© 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. 126299
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods

    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
    ród
    -0.06
    ï¿¥
    -0.06
    ULA
    -0.06
    (æ°´
    -0.06
    ye
    -0.06
    INET
    -0.06
    ÅĻev
    -0.06
     Pols
    -0.06
    Ħ
    -0.06
    anza
    -0.06
    POSITIVE LOGITS
     otherwise
    0.06
    à¹Īà¸Ńม
    0.06
    Interval
    0.06
    ething
    0.06
    ibern
    0.06
    ayet
    0.06
    aptic
    0.06
     Sel
    0.06
    odka
    0.06
    otherwise
    0.06
    Activations Density 0.000%

    No Known Activations