© 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. 119061
    Prev
    Next
    INDEX
    Explanations

    references to cascading style sheets (CSS) within HTML documents

    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
    bidden
    -0.07
    _marshall
    -0.07
    ope
    -0.07
    fifo
    -0.07
    _coin
    -0.06
    richt
    -0.06
    .PLL
    -0.06
    amber
    -0.06
    querque
    -0.06
    thon
    -0.06
    POSITIVE LOGITS
    rette
    0.07
    unan
    0.06
     Therm
    0.06
     Gor
    0.06
     Cher
    0.06
    gor
    0.06
    алеж
    0.06
    ubit
    0.06
    emax
    0.06
    Lite
    0.06
    Activations Density 0.005%

    No Known Activations