© 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. 85644
    Prev
    Next
    INDEX
    Explanations

    inquiries related to decision-making and guidance

    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
    raud
    -0.06
    даÑĤ
    -0.06
    alli
    -0.06
    åķ¦
    -0.06
    ระ
    -0.06
    Dragging
    -0.06
    InBackground
    -0.06
    Reserved
    -0.06
    StatusLabel
    -0.06
     tuned
    -0.06
    POSITIVE LOGITS
     to
    0.12
     να
    0.08
    è¦ģ
    0.08
     best
    0.08
     should
    0.07
    best
    0.07
     Äijá»ĥ
    0.07
    Best
    0.07
    _best
    0.07
    GenerationStrategy
    0.06
    Activations Density 0.019%

    No Known Activations