© 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. 9-LLAMASCOPE-RES-131K
    11. 96800
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components and layout in code

    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
    ozor
    -0.06
     Frid
    -0.06
    -to
    -0.06
    PELL
    -0.06
     butt
    -0.05
     Potter
    -0.05
     Glob
    -0.05
    転
    -0.05
    /spec
    -0.05
     Coverage
    -0.05
    POSITIVE LOGITS
    BuilderFactory
    0.07
    ören
    0.07
    ibold
    0.07
    piel
    0.07
    azzo
    0.07
    ον
    0.06
    owy
    0.06
    zÃŃ
    0.06
    DBObject
    0.06
    öh
    0.06
    Activations Density 0.060%

    No Known Activations