© 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 EvalsExportsinterp-engineNEWAPI 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. 80361
    Prev
    Next
    INDEX
    Explanations

    references to links or resources

    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
    νÏĦ
    -0.06
    281
    -0.06
    pe
    -0.05
    Defaults
    -0.05
     derivative
    -0.05
    heim
    -0.05
    105
    -0.05
    dent
    -0.05
    996
    -0.05
    er
    -0.05
    POSITIVE LOGITS
    /link
    0.12
    (links
    0.08
     link
    0.08
    alink
    0.08
    (Link
    0.08
    .createObject
    0.07
    usaha
    0.07
    /button
    0.07
    ToWorld
    0.07
    ensive
    0.07
    Activations Density 0.009%

    No Known Activations