© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 82390
    Prev
    Next
    INDEX
    Explanations

    references to past experience or knowledge

    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
    responseObject
    -0.07
    IALIZ
    -0.06
     ÄĮer
    -0.06
     Misc
    -0.06
    scar
    -0.06
     again
    -0.06
    scription
    -0.06
    tere
    -0.06
    <typeof
    -0.06
     callable
    -0.06
    POSITIVE LOGITS
    akis
    0.06
    aby
    0.06
     ance
    0.06
    archives
    0.06
    (Collision
    0.06
    ystate
    0.06
    aea
    0.06
    esModule
    0.06
    ç´°
    0.06
    ****↵
    0.06
    Activations Density 0.000%

    No Known Activations