© 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. 15-LLAMASCOPE-RES-131K
    11. 103705
    Prev
    Next
    INDEX
    Explanations

    expressions related to features and details of proposals

    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
    778
    -0.07
    260
    -0.07
    685
    -0.06
    262
    -0.06
    úsqueda
    -0.06
    357
    -0.06
    phies
    -0.06
    239
    -0.06
    266
    -0.06
    abyrin
    -0.06
    POSITIVE LOGITS
    Å¡k
    0.07
    .BLL
    0.07
    alla
    0.07
    _FATAL
    0.07
     cris
    0.06
     proprietary
    0.06
    anford
    0.06
    iç
    0.06
    ãĥ¼ãĥ¬
    0.06
    lier
    0.06
    Activations Density 0.004%

    No Known Activations