© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 2915
    Prev
    Next
    INDEX
    Explanations

    locations or conditions expressed with the word "where."

    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
    zon
    -0.07
    logan
    -0.07
    ointed
    -0.07
    113
    -0.06
    .LoggerFactory
    -0.06
    185
    -0.06
    ansk
    -0.06
    ctype
    -0.06
     nowhere
    -0.06
    lasses
    -0.06
    POSITIVE LOGITS
    ver
    0.08
     nÃło
    0.07
    478
    0.06
    itol
    0.06
    rack
    0.06
    ãĥ³ãĤ¬
    0.06
    regor
    0.06
    emotion
    0.06
    lug
    0.06
    smarty
    0.06
    Activations Density 0.011%

    No Known Activations