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

    Neuronpedia

    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. 4-LLAMASCOPE-RES-32K
    11. 1859
    Prev
    Next
    INDEX
    Explanations

    phrases related to gender identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eward
    -0.18
     yerini
    -0.17
    λμ
    -0.15
    elman
    -0.15
    vala
    -0.15
    вол
    -0.14
    CISION
    -0.14
    lescope
    -0.14
    zes
    -0.14
    ikers
    -0.14
    POSITIVE LOGITS
    ato
    0.16
    uron
    0.15
    macro
    0.15
     Thanh
    0.14
     AAA
    0.14
    arium
    0.14
    648
    0.14
    acles
    0.14
    gu
    0.14
     macro
    0.14
    Activations Density 0.026%

    No Known Activations