© 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. 55286
    Prev
    Next
    INDEX
    Explanations

    indicators of performance or statistical significance

    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
    éı¡
    -0.07
     Buckley
    -0.06
    Lon
    -0.06
     Whit
    -0.06
     nominate
    -0.05
    ugo
    -0.05
    iska
    -0.05
    ë²ł
    -0.05
     ÑħÑĥд
    -0.05
    ley
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.08
    STRU
    0.07
    ibble
    0.07
    afone
    0.07
     considered
    0.07
    lesia
    0.07
    conj
    0.07
    ificate
    0.07
    ocache
    0.07
    cesso
    0.07
    Activations Density 0.008%

    No Known Activations