Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 84401
    Prev
    Next
    INDEX
    Explanations

    descriptions of character depth and complexity

    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
    illis
    -0.07
    izu
    -0.07
    HEST
    -0.07
    ujÄħ
    -0.07
    orent
    -0.06
     пеÑĢен
    -0.06
     himself
    -0.06
    aked
    -0.06
    ubb
    -0.06
     footer
    -0.06
    POSITIVE LOGITS
     themselves
    0.09
    ìĶ©
    0.07
    their
    0.07
     ihre
    0.07
    actable
    0.07
     personalities
    0.06
     their
    0.06
    plib
    0.06
    /actions
    0.06
     Bannon
    0.06
    Activations Density 0.044%

    No Known Activations