© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 16400
    Prev
    Next
    INDEX
    Explanations

    instances of digression or deviation from the main topic of discussion

    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
    è«
    -0.09
    heid
    -0.07
    indow
    -0.06
    leo
    -0.06
    urtle
    -0.06
    /token
    -0.06
    ichte
    -0.06
    ë°
    -0.06
     Hubb
    -0.06
    licted
    -0.06
    POSITIVE LOGITS
     tang
    0.10
     tangent
    0.10
     topic
    0.08
    /topics
    0.08
    .topic
    0.08
    wand
    0.07
     topics
    0.07
     branch
    0.07
     Tang
    0.07
     unrelated
    0.07
    Activations Density 0.032%

    No Known Activations