Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 78353
    Prev
    Next
    INDEX
    Explanations

    various structured data formats and nested data representations

    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
    culo
    -0.06
     æ¼
    -0.06
     Chun
    -0.06
    ÙĪÙĤ
    -0.06
     otherwise
    -0.06
    inand
    -0.06
     povol
    -0.06
     formally
    -0.06
    inite
    -0.06
    atable
    -0.06
    POSITIVE LOGITS
    keh
    0.07
    iator
    0.07
     addCriterion
    0.07
    otionEvent
    0.06
    ansom
    0.06
    .generated
    0.06
    exels
    0.06
    quer
    0.06
    à¤Łà¤ķ
    0.06
     Gee
    0.06
    Activations Density 0.019%

    No Known Activations