© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71542
    Prev
    Next
    INDEX
    Explanations

    comments and annotations in code

    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
    :</
    -0.07
    ohana
    -0.07
    lah
    -0.07
     Levine
    -0.07
    structor
    -0.07
    ıs
    -0.07
    िलन
    -0.07
     Owens
    -0.07
     :</
    -0.07
    :↵↵↵↵↵↵
    -0.07
    POSITIVE LOGITS
     <--
    0.10
     noqa
    0.10
     <-
    0.08
    icina
    0.07
    <-
    0.06
    'gc
    0.06
    dings
    0.06
    eslint
    0.06
     numeral
    0.06
    sic
    0.06
    Activations Density 0.031%

    No Known Activations