© 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. 125421
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or intent regarding actions and decision-making

    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
     not
    -0.07
     instead
    -0.07
     —
    -0.06
     (
    -0.06
     Âł
    -0.06
     almost
    -0.06
     less
    -0.06
     –
    -0.06
     also
    -0.06
     sed
    -0.06
    POSITIVE LOGITS
    以ä¸Ĭ
    0.10
     foregoing
    0.08
     ì§ģìłij
    0.08
     nÃło
    0.08
    ipay
    0.07
    encies
    0.07
    @nate
    0.07
     doÄŁrudan
    0.07
    esome
    0.07
    ourcem
    0.07
    Activations Density 0.022%

    No Known Activations