© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 16084
    Prev
    Next
    INDEX
    Explanations

    instances of offering alternatives or options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndPassword
    -0.07
    %C
    -0.06
     *,↵
    -0.06
    â̦↵
    -0.06
    .github
    -0.06
    ãģķãĤī
    -0.06
    жа
    -0.06
    wich
    -0.06
    夢
    -0.06
    @gmail
    -0.06
    POSITIVE LOGITS
    pNet
    0.07
    cesso
    0.07
    Smarty
    0.07
    NotSupportedException
    0.07
     /*č↵
    0.07
    achuset
    0.07
    jeta
    0.07
     DISCLAIM
    0.07
    avras
    0.07
    croll
    0.06
    Activations Density 0.078%

    No Known Activations