© 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. 86715
    Prev
    Next
    INDEX
    Explanations

    positive assessments or ratings

    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
    trys
    -0.07
     Monk
    -0.06
    ous
    -0.06
    è¦ļ
    -0.06
     Statistics
    -0.06
    fix
    -0.06
    ujet
    -0.06
    swire
    -0.06
     Identifier
    -0.06
    hog
    -0.06
    POSITIVE LOGITS
     hereby
    0.08
    pter
    0.08
    dech
    0.07
     bonus
    0.06
    eller
    0.06
     pathMatch
    0.06
    unger
    0.06
    infeld
    0.06
    dling
    0.06
    ller
    0.06
    Activations Density 0.020%

    No Known Activations