© 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. 70938
    Prev
    Next
    INDEX
    Explanations

    numeric values or high significance indicators

    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
     carc
    -0.07
    oti
    -0.07
     सल
    -0.07
    ardu
    -0.06
    arel
    -0.06
     è©ķ価
    -0.06
    OLOR
    -0.06
    ëĿ¼íĶ¼
    -0.06
    Codes
    -0.06
    ardi
    -0.06
    POSITIVE LOGITS
     Japan
    0.09
     Mits
    0.08
     prefect
    0.07
    peror
    0.07
    zew
    0.07
    Japan
    0.07
     Lawson
    0.07
     Tokyo
    0.07
     Hats
    0.07
     Buddhist
    0.07
    Activations Density 0.000%

    No Known Activations