© 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. 40197
    Prev
    Next
    INDEX
    Explanations

    references to baseline measurements or comparisons in a structured context

    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
    ÂłS
    -0.06
    ,\↵
    -0.06
     :č↵
    -0.06
    ÂłE
    -0.05
     eighty
    -0.05
     Pat
    -0.05
     Sid
    -0.05
    _SMS
    -0.05
     ↵↵
    -0.05
     dy
    -0.05
    POSITIVE LOGITS
     mastur
    0.08
    iyah
    0.07
    erç
    0.07
    gis
    0.07
    ispiel
    0.07
    riba
    0.07
    iyas
    0.07
    redit
    0.07
    ilion
    0.07
    @student
    0.07
    Activations Density 0.000%

    No Known Activations