© 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. 126775
    Prev
    Next
    INDEX
    Explanations

    instances of the word "contributing" and its variations, indicating involvement or authorship

    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
    acr
    -0.07
     Grat
    -0.07
    nier
    -0.07
    enson
    -0.07
    Conv
    -0.06
    illo
    -0.06
    oge
    -0.06
    ỳ
    -0.06
    imeo
    -0.06
    ipher
    -0.06
    POSITIVE LOGITS
    athers
    0.07
     contributed
    0.07
    ToArray
    0.06
     greatly
    0.06
    ington
    0.06
    ATO
    0.06
    _IMPORT
    0.06
     Tes
    0.06
    contrib
    0.06
    urret
    0.06
    Activations Density 0.005%

    No Known Activations