© 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. 94256
    Prev
    Next
    INDEX
    Explanations

    mentions of specific banks and 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
    ê±°ëŀĺê°Ģ
    -0.09
    buz
    -0.08
    vÄĽ
    -0.07
    MUX
    -0.07
    ãģĭãĤı
    -0.07
    ptoms
    -0.07
    ä¹ĥ
    -0.07
    ---</
    -0.07
    ----</
    -0.07
    rtl
    -0.07
    POSITIVE LOGITS
     Perkins
    0.07
    âĢij
    0.06
    0.06
    tek
    0.05
    Âł
    0.05
     âĢ¢
    0.05
     detail
    0.05
    ikk
    0.05
    kad
    0.05
     (
    0.05
    Activations Density 0.026%

    No Known Activations