© 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. 95325
    Prev
    Next
    INDEX
    Explanations

    instances of counting or detailed comparisons in the text

    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
    缼
    -0.09
    énom
    -0.08
    ukkit
    -0.08
     nrw
    -0.08
    hlas
    -0.08
    gien
    -0.08
    ichern
    -0.08
    upo
    -0.07
    agnar
    -0.07
    ÏĥοÏħ
    -0.07
    POSITIVE LOGITS
     found
    0.11
    found
    0.09
     Found
    0.09
    Found
    0.08
     ended
    0.08
    find
    0.07
     came
    0.07
     turns
    0.07
     eventually
    0.07
     FOUND
    0.07
    Activations Density 0.031%

    No Known Activations