© 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. 86496
    Prev
    Next
    INDEX
    Explanations

    references to web directories and 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
    ÏĦε
    -0.07
    unkt
    -0.06
     r
    -0.06
    ARD
    -0.06
    ants
    -0.06
    usc
    -0.06
    inha
    -0.06
     trous
    -0.05
    tam
    -0.05
    orners
    -0.05
    POSITIVE LOGITS
    pac
    0.07
     alacak
    0.07
    igue
    0.07
    rim
    0.07
     Ellis
    0.07
    [__
    0.06
    ãģĵãģĿ
    0.06
    etros
    0.06
     Affero
    0.06
    andle
    0.06
    Activations Density 0.000%

    No Known Activations