© 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. 107483
    Prev
    Next
    INDEX
    Explanations

    geographical and city-related terms

    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
    aho
    -0.08
    ãĤ«ãĥ¼
    -0.07
    大åħ¨
    -0.07
    alam
    -0.07
    ãĥ¼ãĤ¯
    -0.07
    rious
    -0.07
    xes
    -0.06
    NotSupportedException
    -0.06
    ãĥ¼ãĤº
    -0.06
    evin
    -0.06
    POSITIVE LOGITS
    ISCO
    0.07
    Ñģкой
    0.07
    _ANY
    0.06
     lights
    0.06
    sm
    0.06
    level
    0.06
    wide
    0.06
     gran
    0.06
    ิว
    0.06
     suburbs
    0.06
    Activations Density 0.016%

    No Known Activations