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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 20-LLAMASCOPE-RES-32K
    11. 21216
    Prev
    Next
    INDEX
    Explanations

    references to biases and equality issues within social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    configs
    -0.14
    ÏĥοÏħ
    -0.13
    047
    -0.12
    ÏĢλ
    -0.12
    thew
    -0.12
    helpers
    -0.12
    053
    -0.12
     feather
    -0.12
    pagen
    -0.12
    DMIN
    -0.12
    POSITIVE LOGITS
    MESS
    0.15
    culo
    0.15
     Byl
    0.14
    otto
    0.14
    jed
    0.13
    rello
    0.13
    ellow
    0.12
    raquo
    0.12
     Barry
    0.12
    iá»ĥm
    0.12
    Activations Density 0.560%

    No Known Activations