© 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. 90432
    Prev
    Next
    INDEX
    Explanations

    headers and section markers in a document

    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
    еÑı
    -0.07
    iom
    -0.07
    óng
    -0.06
    zym
    -0.06
    iye
    -0.06
    ester
    -0.06
     facto
    -0.06
     пÑĢоп
    -0.06
    lio
    -0.06
    oy
    -0.06
    POSITIVE LOGITS
     prelim
    0.08
    anje
    0.07
     olanlar
    0.06
    yntax
    0.06
    ASA
    0.06
    CLUDING
    0.06
    lef
    0.06
    shal
    0.06
     ActiveForm
    0.06
     Uh
    0.06
    Activations Density 0.006%

    No Known Activations