© 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. 84238
    Prev
    Next
    INDEX
    Explanations

    words related to questions, tasks, and problem-solving

    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
    ¢°
    -0.07
    lea
    -0.06
    ceed
    -0.06
    odos
    -0.06
    Insensitive
    -0.06
    UND
    -0.06
    etch
    -0.06
    ادÙħ
    -0.06
    ui
    -0.06
    UI
    -0.06
    POSITIVE LOGITS
    GX
    0.07
    swith
    0.07
    -mf
    0.06
    jam
    0.06
     Rum
    0.06
    Impossible
    0.06
    Ñıж
    0.06
    656
    0.06
    óc
    0.06
    ograd
    0.06
    Activations Density 0.047%

    No Known Activations