© 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. 18199
    Prev
    Next
    INDEX
    Explanations

    programming syntax and technical function calls

    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
    лÑİд
    -0.08
    ebi
    -0.07
    InternalServerError
    -0.06
    seau
    -0.06
     putas
    -0.06
    ãn
    -0.06
    eed
    -0.06
     θε
    -0.06
    á»įt
    -0.06
     transform
    -0.06
    POSITIVE LOGITS
     Connect
    0.08
    .connect
    0.08
     connect
    0.07
    anson
    0.07
    _connect
    0.07
    connect
    0.07
     connection
    0.07
     Establish
    0.07
     establishing
    0.07
     connecting
    0.07
    Activations Density 0.045%

    No Known Activations