© 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. 84048
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to court decisions

    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
    TEGER
    -0.07
    Untitled
    -0.07
    emmel
    -0.07
     Cous
    -0.06
    fiber
    -0.06
     prol
    -0.06
     favorites
    -0.06
    ï¿¥
    -0.06
    asiswa
    -0.06
    isman
    -0.06
    POSITIVE LOGITS
    (AP
    0.08
    asz
    0.07
    ách
    0.07
    icha
    0.06
    или
    0.06
    atisation
    0.06
    mán
    0.06
     grouping
    0.06
     гол
    0.06
    etti
    0.06
    Activations Density 0.006%

    No Known Activations