© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106109
    Prev
    Next
    INDEX
    Explanations

    references to prior statements or suggestions

    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
    ucci
    -0.07
    alth
    -0.06
    -io
    -0.06
     allegedly
    -0.06
    _ASSUME
    -0.06
    ãĥ³ãĥIJ
    -0.06
    .omg
    -0.06
    itone
    -0.06
     Deck
    -0.06
    约
    -0.06
    POSITIVE LOGITS
     suggestion
    0.08
     excellent
    0.08
     above
    0.07
    above
    0.07
     ìľĦ
    0.06
     answer
    0.06
     ìĽĥ
    0.06
     (+
    0.06
     suggested
    0.06
    cape
    0.06
    Activations Density 0.007%

    No Known Activations