© 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. 125443
    Prev
    Next
    INDEX
    Explanations

    references to forward-looking statements related to business or financial forecasts

    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
    /AP
    -0.06
    hall
    -0.06
     Permit
    -0.06
     uncon
    -0.06
    ming
    -0.06
    GetString
    -0.06
    overe
    -0.06
    741
    -0.05
    840
    -0.05
    ieux
    -0.05
    POSITIVE LOGITS
     statements
    0.07
    ateg
    0.07
    SetBranch
    0.07
    atement
    0.07
    _statement
    0.07
    еÑĢп
    0.07
    TriState
    0.07
    _SUITE
    0.06
    obl
    0.06
     Statements
    0.06
    Activations Density 0.001%

    No Known Activations