© 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. 118596
    Prev
    Next
    INDEX
    Explanations

    references to statistical data and numerical values

    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
     Recon
    -0.07
    avou
    -0.06
     setbacks
    -0.06
     sof
    -0.06
    oldown
    -0.06
    Ľi
    -0.06
    idget
    -0.06
    XmlAttribute
    -0.06
    iscard
    -0.06
     ifndef
    -0.06
    POSITIVE LOGITS
    [email
    0.08
    usu
    0.07
    orem
    0.07
    uda
    0.07
    ÑĦоÑĢми
    0.07
    ukan
    0.06
    ota
    0.06
    uido
    0.06
    umatic
    0.06
    semblies
    0.06
    Activations Density 0.008%

    No Known Activations