© 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. 78299
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "someone" in various contexts

    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
    .scalablytyped
    -0.08
    [color
    -0.07
    #
    -0.07
    phem
    -0.07
     lá»ĩ
    -0.07
    ynchronously
    -0.07
     Require
    -0.07
    .contrib
    -0.06
    juana
    -0.06
    using
    -0.06
    POSITIVE LOGITS
     else
    0.11
    else
    0.07
    (s
    0.07
     somewhere
    0.07
     ELSE
    0.06
    _else
    0.06
     dim
    0.06
    462
    0.06
    ae
    0.06
    278
    0.06
    Activations Density 0.013%

    No Known Activations