© 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. 5-LLAMASCOPE-RES-131K
    11. 126538
    Prev
    Next
    INDEX
    Explanations

    references to specific medical studies and conditions

    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
    yny
    -0.07
    acha
    -0.06
    gart
    -0.06
    istrovstvÃŃ
    -0.06
    /locale
    -0.06
    ائÙĤ
    -0.06
    igaret
    -0.06
    íı°
    -0.06
    endum
    -0.06
    ensity
    -0.06
    POSITIVE LOGITS
    TypeInfo
    0.07
    iah
    0.06
    OperationException
    0.06
    826
    0.06
    ukarı
    0.06
     Ross
    0.06
    ondere
    0.06
    CONTENT
    0.06
    ounty
    0.06
     SEXP
    0.06
    Activations Density 0.008%

    No Known Activations