© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 16326
    Prev
    Next
    INDEX
    Explanations

    articles preceding nouns indicating significant concepts or categories

    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
    ies
    -0.07
     subsequ
    -0.07
     ones
    -0.07
    iez
    -0.07
    idor
    -0.07
    ãĤĪãģĨãģ«
    -0.07
    ÑĨÑĥ
    -0.06
    eses
    -0.06
    jes
    -0.06
    nowledge
    -0.06
    POSITIVE LOGITS
    coli
    0.07
    ëį°
    0.07
    acent
    0.07
    /tiny
    0.07
     Thing
    0.07
    antity
    0.07
    ITY
    0.06
    лим
    0.06
    Ł
    0.06
    orex
    0.06
    Activations Density 0.012%

    No Known Activations