© 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 EvalsExportsAPI 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. 87486
    Prev
    Next
    INDEX
    Explanations

    locations and instructions related to documents or pages

    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
    line
    -0.07
    liers
    -0.06
    sten
    -0.06
    merce
    -0.06
    wards
    -0.06
     epid
    -0.06
    ldkf
    -0.06
    ilyn
    -0.06
    sburg
    -0.06
    erc
    -0.05
    POSITIVE LOGITS
     cest
    0.07
    amaz
    0.07
    DBObject
    0.07
     wet
    0.07
     Wet
    0.07
    ACLE
    0.07
    Deserializer
    0.07
    SCO
    0.07
    á»ĭ
    0.06
    CEE
    0.06
    Activations Density 0.003%

    No Known Activations