© 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. 18368
    Prev
    Next
    INDEX
    Explanations

    references to towns and communities, particularly in relation to events or activities occurring in those areas

    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
     ucwords
    -0.08
    elper
    -0.08
    .createClass
    -0.07
    laden
    -0.07
     COPYING
    -0.07
    itary
    -0.07
    važ
    -0.07
    /math
    -0.07
    -INF
    -0.07
    iš
    -0.07
    POSITIVE LOGITS
     syndrome
    0.09
     Syndrome
    0.09
    /big
    0.07
    ersed
    0.07
    /high
    0.06
    /full
    0.06
    -low
    0.06
    /small
    0.06
    aus
    0.05
    undred
    0.05
    Activations Density 0.099%

    No Known Activations