© 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. 15-LLAMASCOPE-RES-131K
    11. 61733
    Prev
    Next
    INDEX
    Explanations

    references to catalogs or lists of items

    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
    ibold
    -0.07
    chet
    -0.07
    ibia
    -0.06
    assen
    -0.06
    umas
    -0.06
     somehow
    -0.06
    rott
    -0.06
    (CType
    -0.06
    midt
    -0.06
    wie
    -0.06
    POSITIVE LOGITS
    ewis
    0.07
    ï¸
    0.07
    attern
    0.06
    iyas
    0.06
    å¹
    0.06
    à¹īà¸Ķ
    0.06
    esin
    0.06
    away
    0.06
    eenth
    0.06
    bjerg
    0.06
    Activations Density 0.000%

    No Known Activations