© 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 EvalsExportsinterp-engineNEWAPI 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. 62863
    Prev
    Next
    INDEX
    Explanations

    elements related to interpersonal interactions and the indirect effects of actions or situations

    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
    aklı
    -0.07
    ãģªãģĮ
    -0.07
    /Foundation
    -0.07
    uzey
    -0.07
    _vlog
    -0.07
    ezi
    -0.07
    prung
    -0.07
    _lex
    -0.07
    _Construct
    -0.07
    lz
    -0.07
    POSITIVE LOGITS
    ynchronously
    0.07
     often
    0.06
    psilon
    0.06
     sometimes
    0.06
     classical
    0.06
    ogany
    0.06
     xtype
    0.06
    go
    0.05
    ãĤ©
    0.05
     kind
    0.05
    Activations Density 0.054%

    No Known Activations