© 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. 126903
    Prev
    Next
    INDEX
    Explanations

    mentions of media and journalism entities or roles

    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
     _____
    -0.07
    ahat
    -0.07
    cale
    -0.07
    fect
    -0.06
     itself
    -0.06
    ho
    -0.06
    thern
    -0.06
    -themed
    -0.06
    ÑĪев
    -0.06
    cales
    -0.06
    POSITIVE LOGITS
    PropTypes
    0.08
    .scalablytyped
    0.07
     correspondent
    0.07
    canf
    0.07
    /std
    0.07
     contributing
    0.07
    ARN
    0.07
     기ìŀIJ
    0.07
    è¿ĩæĿ¥
    0.07
    contrib
    0.06
    Activations Density 0.013%

    No Known Activations