© 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. 106892
    Prev
    Next
    INDEX
    Explanations

    instances of code that involve disabling functionality or settings

    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
    entine
    -0.08
    eil
    -0.08
    illiseconds
    -0.07
    Ậ
    -0.07
    toi
    -0.07
    roperties
    -0.07
    .Reporting
    -0.07
    िण
    -0.07
    ents
    -0.07
    ¦¬
    -0.07
    POSITIVE LOGITS
    ment
    0.11
    /disable
    0.09
    æİī
    0.09
    /dis
    0.08
    VertexAttribArray
    0.07
     altogether
    0.06
    birth
    0.06
    ments
    0.06
    /un
    0.06
    163
    0.06
    Activations Density 0.012%

    No Known Activations