© 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. 57276
    Prev
    Next
    INDEX
    Explanations

    technical identifiers or keywords related to programming or code structures

    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
    e
    -0.09
    ed
    -0.09
    es
    -0.08
    endi
    -0.07
    eda
    -0.07
    agy
    -0.07
    s
    -0.07
    IDI
    -0.07
    umbnails
    -0.06
    htdocs
    -0.06
    POSITIVE LOGITS
    lict
    0.06
    ivery
    0.06
    جار
    0.06
     helicopt
    0.06
    ronic
    0.06
    ITHER
    0.06
     Shades
    0.06
     substance
    0.06
    istrovstvÃŃ
    0.06
    OfClass
    0.06
    Activations Density 0.001%

    No Known Activations