© 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. 120469
    Prev
    Next
    INDEX
    Explanations

    words related to outcomes or consequences

    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
     dán
    -0.06
    agr
    -0.06
    683
    -0.06
    pd
    -0.06
    uso
    -0.06
    -ne
    -0.06
    sek
    -0.06
    uple
    -0.06
     поÑĪ
    -0.06
    pred
    -0.06
    POSITIVE LOGITS
    _Tis
    0.07
    _Lean
    0.07
    ToSelector
    0.07
    gers
    0.07
    BitFields
    0.06
    SI
    0.06
    Nam
    0.06
    enthal
    0.06
    OffsetTable
    0.06
    äng
    0.06
    Activations Density 0.009%

    No Known Activations