© 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. 17-LLAMASCOPE-RES-131K
    11. 77492
    Prev
    Next
    INDEX
    Explanations

    phrases indicating support or resources for various groups and activities

    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
    abaj
    -0.07
    ahoma
    -0.07
    azzo
    -0.07
    pu
    -0.07
    ailable
    -0.07
    ithmetic
    -0.07
    steen
    -0.07
    OutOf
    -0.06
    ROOM
    -0.06
     ÎĶημο
    -0.06
    POSITIVE LOGITS
     accompanied
    0.07
     bic
    0.06
     interested
    0.06
    icap
    0.06
    fleet
    0.06
     titled
    0.06
     scores
    0.06
    λÏĮ
    0.06
     entitled
    0.05
    /about
    0.05
    Activations Density 0.023%

    No Known Activations