© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 91526
    Prev
    Next
    INDEX
    Explanations

    adverbs that describe manner or quality of action

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    (strtolower
    -0.08
    Alive
    -0.07
    orges
    -0.07
    unar
    -0.06
    eses
    -0.06
     Pon
    -0.06
    quest
    -0.06
    gorm
    -0.06
    IBE
    -0.06
    ESH
    -0.06
    POSITIVE LOGITS
    /il
    0.08
     manner
    0.07
    wahl
    0.07
    -than
    0.06
    /at
    0.06
    ness
    0.06
    ÄĽÅĻ
    0.06
    481
    0.06
    aurus
    0.06
    ãĥ¼ãĥĹ
    0.06
    Activations Density 0.027%

    No Known Activations