© 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. 41758
    Prev
    Next
    INDEX
    Explanations

    mentions of tall individuals or characters

    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
    entially
    -0.07
    ethe
    -0.07
    ettings
    -0.07
    icari
    -0.07
    wcs
    -0.07
    eax
    -0.07
    etu
    -0.06
    ouro
    -0.06
    elial
    -0.06
    elyn
    -0.06
    POSITIVE LOGITS
    ented
    0.08
    ened
    0.08
     Tall
    0.07
    ahas
    0.07
    enburg
    0.07
    boys
    0.07
    boy
    0.07
    abor
    0.07
    ied
    0.07
    ies
    0.07
    Activations Density 0.004%

    No Known Activations