© 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. 15-LLAMASCOPE-RES-131K
    6. 103685
    Prev
    Next
    INDEX
    Explanations

    specific formatting and structure elements in text, such as lists and bullet points

    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
     Uncategorized
    -0.08
     etc
    -0.06
    lay
    -0.06
    unt
    -0.06
    igm
    -0.06
     studio
    -0.06
    etc
    -0.06
     plain
    -0.06
    ings
    -0.06
    .CopyTo
    -0.06
    POSITIVE LOGITS
    elib
    0.07
     olmayan
    0.07
    ylko
    0.07
     нада
    0.07
    /***/
    0.07
     also
    0.07
    imuth
    0.07
    ibri
    0.07
    ostel
    0.07
    emale
    0.07
    Activations Density 0.101%

    No Known Activations