© 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. 27780
    Prev
    Next
    INDEX
    Explanations

    occurrences of the abbreviation "Dr." followed by a name

    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
    714
    -0.06
    emey
    -0.06
    crease
    -0.06
    ker
    -0.06
    chant
    -0.06
    æħ
    -0.06
    428
    -0.06
    713
    -0.06
    ston
    -0.06
     fi
    -0.06
    POSITIVE LOGITS
    .ab
    0.08
    eÅŁ
    0.07
    izr
    0.07
    eel
    0.07
    odesk
    0.06
    utos
    0.06
    scious
    0.06
    ladıģı
    0.06
    vailability
    0.06
    oldem
    0.06
    Activations Density 0.001%

    No Known Activations