© 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. 106846
    Prev
    Next
    INDEX
    Explanations

    references to numerical information and web addresses

    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
    ató
    -0.06
    he
    -0.06
    tr
    -0.06
    anse
    -0.06
    æĭľ
    -0.06
    ookie
    -0.05
    วà¸Ķ
    -0.05
    U
    -0.05
    ĨĴ
    -0.05
    itel
    -0.05
    POSITIVE LOGITS
     www
    0.09
    ,www
    0.09
    ãĥ¼ãĤ¸
    0.08
    .www
    0.07
    www
    0.07
    uder
    0.07
    RunLoop
    0.07
    /www
    0.07
    turnstile
    0.07
    iete
    0.07
    Activations Density 0.004%

    No Known Activations