© 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. 78804
    Prev
    Next
    INDEX
    Explanations

    statements or phrases indicating rates, rankings, or high achievements

    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
    âĢļ
    -0.06
     же
    -0.06
    áo
    -0.06
    udu
    -0.06
    ây
    -0.06
    Æ¡
    -0.06
    ẻ
    -0.06
    __
    -0.06
    ase
    -0.06
    oret
    -0.06
    POSITIVE LOGITS
    202
    0.12
    201
    0.11
     Uncategorized
    0.08
    iqueta
    0.07
     ActiveForm
    0.07
    ForObject
    0.07
     EntityState
    0.07
     ’
    0.07
    iare
    0.07
     unc
    0.07
    Activations Density 0.029%

    No Known Activations