© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 82995
    Prev
    Next
    INDEX
    Explanations

    action verbs related to baseball plays

    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
    emer
    -0.07
    locker
    -0.07
    gard
    -0.07
    abcdefghijkl
    -0.07
    brook
    -0.06
    貸
    -0.06
    erot
    -0.06
    é¤Ĭ
    -0.06
     sav
    -0.06
    ataka
    -0.06
    POSITIVE LOGITS
    bedo
    0.06
     seb
    0.06
    ime
    0.06
    ATIC
    0.06
    RITE
    0.06
     playable
    0.06
    nÃŃ
    0.06
    ÎŃλ
    0.06
    _SOFT
    0.06
    रण
    0.06
    Activations Density 0.009%

    No Known Activations