© 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. 75171
    Prev
    Next
    INDEX
    Explanations

    hashtags or numbering in text

    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
    NotFoundError
    -0.07
    ķĮ
    -0.07
    ikit
    -0.07
     нал
    -0.07
    zek
    -0.06
    交
    -0.06
    rescia
    -0.06
    ikk
    -0.06
    ãĥ«ãĥķ
    -0.06
    uyu
    -0.06
    POSITIVE LOGITS
     sourceMappingURL
    0.07
    .#
    0.07
    ,#
    0.07
    elli
    0.07
    yte
    0.07
    ï¾Ł
    0.06
    aná
    0.06
     noqa
    0.06
    hashtags
    0.06
    ifdef
    0.06
    Activations Density 0.020%

    No Known Activations