© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77417
    Prev
    Next
    INDEX
    Explanations

    relationships to categories of healthcare and wellness, specifically related to eye care

    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
    lef
    -0.07
    ãĥķãĥĪ
    -0.07
    opies
    -0.07
    Immutable
    -0.07
    اساÙĨ
    -0.06
    IFT
    -0.06
    unan
    -0.06
    ukan
    -0.06
    èĬ¸
    -0.06
    ABCDE
    -0.06
    POSITIVE LOGITS
    ¢åįķ
    0.07
    ĮĢ
    0.06
     Ear
    0.06
    nock
    0.06
    ayar
    0.06
    adir
    0.06
    Ñĵ
    0.06
    $MESS
    0.06
    jective
    0.06
    itchens
    0.06
    Activations Density 0.164%

    No Known Activations