© 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. 15-LLAMASCOPE-RES-131K
    11. 87869
    Prev
    Next
    INDEX
    Explanations

    timestamps and date-related information

    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
    .zh
    -0.06
    cky
    -0.06
    .emp
    -0.06
    ![
    -0.06
    .peer
    -0.06
     reins
    -0.06
    .executeQuery
    -0.06
     racket
    -0.05
    nothrow
    -0.05
    herits
    -0.05
    POSITIVE LOGITS
    zcze
    0.08
    aliz
    0.07
    ı
    0.07
    YM
    0.06
    rie
    0.06
    decorate
    0.06
    ippo
    0.06
    quivo
    0.06
    åĹ
    0.06
    legate
    0.06
    Activations Density 0.001%

    No Known Activations