© 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. 40827
    Prev
    Next
    INDEX
    Explanations

    references to significant achievements of women in political history

    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
    abeth
    -0.07
    ATAB
    -0.07
     GOODMAN
    -0.07
    ëŀį
    -0.07
    NetMessage
    -0.07
     screens
    -0.07
    vette
    -0.07
    leases
    -0.07
    leased
    -0.06
    SCREEN
    -0.06
    POSITIVE LOGITS
    184
    0.07
    183
    0.07
    185
    0.07
     office
    0.06
     State
    0.06
     Swing
    0.06
    -invalid
    0.06
     Tec
    0.06
     state
    0.06
    187
    0.06
    Activations Density 0.009%

    No Known Activations