© 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. 129241
    Prev
    Next
    INDEX
    Explanations

    educational qualifications, specifically degrees

    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
    curity
    -0.07
    engeance
    -0.07
    656
    -0.07
    /he
    -0.07
    quiet
    -0.07
    406
    -0.06
    embers
    -0.06
    /Math
    -0.06
    463
    -0.06
    fried
    -0.06
    POSITIVE LOGITS
    dbg
    0.08
    andles
    0.07
    ANDLE
    0.07
    idian
    0.06
    çĪ½
    0.06
     strchr
    0.06
     huz
    0.06
    alian
    0.06
    ÃŃk
    0.06
     ÑĤака
    0.06
    Activations Density 0.004%

    No Known Activations