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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 27338
    Prev
    Next
    INDEX
    Explanations

    sequences of actions in instructional or procedural text

    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
     ëĦ¤ìĿ´íĬ¸
    -0.07
    nip
    -0.07
    ilon
    -0.06
    eldom
    -0.06
     odense
    -0.06
    pot
    -0.06
    /gin
    -0.06
     fetisch
    -0.06
    kap
    -0.06
     coquine
    -0.06
    POSITIVE LOGITS
    ysz
    0.07
    _tl
    0.06
    .IsValid
    0.06
    opes
    0.06
    oteca
    0.06
    imuth
    0.06
    eid
    0.06
    .plugin
    0.06
    ichert
    0.06
     Doub
    0.06
    Activations Density 0.031%

    No Known Activations