© 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. 28986
    Prev
    Next
    INDEX
    Explanations

    symbols and ellipsis indicating omitted or incomplete text

    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
    ãĥ¼ãĥĪ
    -0.06
    iddy
    -0.06
     trav
    -0.06
    ffen
    -0.05
    éī
    -0.05
    hani
    -0.05
    vÄĽt
    -0.05
    .spawn
    -0.05
     Kraft
    -0.05
     East
    -0.05
    POSITIVE LOGITS
    ç¿Ķ
    0.07
    IVES
    0.07
    lead
    0.07
    kart
    0.07
    ANE
    0.07
    ude
    0.07
    ãĥ³ãĥĸ
    0.07
    /commons
    0.07
    meer
    0.06
    оÑĢа
    0.06
    Activations Density 0.002%

    No Known Activations