© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-32K
    11. 28635
    Prev
    Next
    INDEX
    Explanations

    themes related to social justice and discrimination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases describing discrimination, prejudice, or unfair treatment based on identity characteristics.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atee
    -0.15
    ĥn
    -0.15
    lc
    -0.14
    nums
    -0.14
     Morg
    -0.14
     pH
    -0.13
    iego
    -0.13
    .NULL
    -0.13
    pressive
    -0.13
     ä¹
    -0.13
    POSITIVE LOGITS
    ÑģиÑĤ
    0.15
    plib
    0.15
     perceived
    0.15
    977
    0.15
    моÑģ
    0.14
     unconventional
    0.14
    оба
    0.14
    रत
    0.14
     Seah
    0.14
     abnormal
    0.14
    Activations Density 0.113%

    No Known Activations