© 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. 62275
    Prev
    Next
    INDEX
    Explanations

    instances of the equal sign

    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
    ategor
    -0.08
    -Ta
    -0.07
    ãĥ£
    -0.07
     гÑĥб
    -0.07
    ILER
    -0.07
    PTH
    -0.07
    .glide
    -0.07
    ków
    -0.07
    ayah
    -0.07
    ết
    -0.06
    POSITIVE LOGITS
    ardy
    0.06
    axon
    0.06
    urat
    0.06
     Gard
    0.06
    onto
    0.06
    iland
    0.06
     Sau
    0.06
    ddy
    0.06
    ienne
    0.05
    ullen
    0.05
    Activations Density 0.028%

    No Known Activations