© 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. 118397
    Prev
    Next
    INDEX
    Explanations

    inquiries directed towards government officials regarding specific issues or actions

    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
    ritz
    -0.07
    nock
    -0.07
     Britt
    -0.07
    stag
    -0.07
    ienes
    -0.06
    ACES
    -0.06
    iero
    -0.06
    prec
    -0.06
     Farmers
    -0.06
    λί
    -0.06
    POSITIVE LOGITS
    ernote
    0.07
    alaxy
    0.06
    reative
    0.06
    oldemort
    0.06
    unami
    0.06
    .localized
    0.06
    _SUPPLY
    0.06
     Trudeau
    0.06
    _define
    0.06
    ολ
    0.06
    Activations Density 0.004%

    No Known Activations