© 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. 55862
    Prev
    Next
    INDEX
    Explanations

    references to categories or classifications in a structured format

    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
    463
    -0.07
    idth
    -0.06
    VertexAttrib
    -0.06
    aku
    -0.06
    ÎŃÏģγ
    -0.06
    owan
    -0.06
    rew
    -0.06
    Clickable
    -0.06
    yy
    -0.06
     Kre
    -0.06
    POSITIVE LOGITS
    _pickle
    0.07
    kok
    0.07
    ãĥ¼ãĥĨ
    0.07
    antlr
    0.06
     casc
    0.06
    ceb
    0.06
    tw
    0.06
    cano
    0.06
    lice
    0.06
    essen
    0.06
    Activations Density 0.000%

    No Known Activations