© 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. 119147
    Prev
    Next
    INDEX
    Explanations

    numerical data related to view counts and ratings

    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
    olini
    -0.07
    Getty
    -0.06
    ượng
    -0.06
    ç²¾
    -0.06
    atts
    -0.06
    sit
    -0.06
     èIJ¬
    -0.06
     somew
    -0.06
     congress
    -0.06
    бол
    -0.06
    POSITIVE LOGITS
    dna
    0.07
    poi
    0.07
    axy
    0.07
    isure
    0.07
    mine
    0.07
    nave
    0.07
    igans
    0.07
     Sleeve
    0.07
    mÃŃn
    0.07
    amon
    0.07
    Activations Density 0.014%

    No Known Activations