© 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. 106149
    Prev
    Next
    INDEX
    Explanations

    actions and interactions involving animate characters or entities

    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
    ecko
    -0.09
    rame
    -0.08
    rael
    -0.07
    abbr
    -0.07
    vider
    -0.07
    ecast
    -0.07
    empor
    -0.06
    .vs
    -0.06
     inform
    -0.06
     teg
    -0.06
    POSITIVE LOGITS
     entr
    0.07
    ãģĹãĤĩ
    0.06
    à¸Ķà¸Ļ
    0.06
    SED
    0.06
     Pac
    0.06
     FAT
    0.06
    olynomial
    0.06
    .resume
    0.06
     Rig
    0.06
    /LICENSE
    0.06
    Activations Density 0.007%

    No Known Activations