© 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. 107576
    Prev
    Next
    INDEX
    Explanations

    key elements and details related to community events

    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
    ÅĻÃŃ
    -0.06
    inde
    -0.06
     Din
    -0.06
    pag
    -0.06
     DIN
    -0.06
     Weekend
    -0.06
    ripp
    -0.06
     podcasts
    -0.06
     din
    -0.05
    ãĤ·ãĤ¢
    -0.05
    POSITIVE LOGITS
    leitung
    0.07
    ichert
    0.07
     we
    0.07
    .obtain
    0.07
    egasus
    0.07
    (mapping
    0.07
    styl
    0.07
     bri
    0.07
    YL
    0.07
     tá»iji
    0.07
    Activations Density 0.029%

    No Known Activations