© 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. 128580
    Prev
    Next
    INDEX
    Explanations

    references to gas-related topics

    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
    eer
    -0.07
    hone
    -0.07
    een
    -0.07
    IENTATION
    -0.07
    eper
    -0.07
    ashboard
    -0.07
    alls
    -0.07
    avic
    -0.07
    instein
    -0.07
    isms
    -0.06
    POSITIVE LOGITS
    oline
    0.10
    olina
    0.10
    (es
    0.09
    ëŁī
    0.07
    nier
    0.07
    olin
    0.07
    ier
    0.07
    ified
    0.07
    igue
    0.07
    arith
    0.07
    Activations Density 0.006%

    No Known Activations