© 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. 27069
    Prev
    Next
    INDEX
    Explanations

    internet domain names and related web addresses

    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
    isz
    -0.08
    mlin
    -0.07
    zo
    -0.07
    ifer
    -0.07
    ife
    -0.07
    kur
    -0.06
    ags
    -0.06
    ledon
    -0.06
    uso
    -0.06
    lsru
    -0.06
    POSITIVE LOGITS
    .synthetic
    0.08
    istrovstvÃŃ
    0.07
     fitte
    0.07
    ónico
    0.07
    enal
    0.07
    rete
    0.07
    nard
    0.06
    iá»ĥn
    0.06
     Gor
    0.06
    ystack
    0.06
    Activations Density 0.001%

    No Known Activations