© 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. 74846
    Prev
    Next
    INDEX
    Explanations

    questions and phrases related to seeking information or locations

    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
    aspberry
    -0.07
    itta
    -0.07
    ippy
    -0.06
    anon
    -0.06
    EDITOR
    -0.06
    cep
    -0.06
    ве
    -0.06
    iele
    -0.06
    bons
    -0.06
    eph
    -0.06
    POSITIVE LOGITS
    ãĥ«ãĥĪ
    0.07
    _WM
    0.07
    ÙĦÛĮÙĩ
    0.07
     Kushner
    0.07
     Murdoch
    0.06
    GMEM
    0.06
     moż
    0.06
     hod
    0.06
    gable
    0.06
    GP
    0.06
    Activations Density 0.008%

    No Known Activations