© 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. 54983
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the necessity or effort involved in achieving something

    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
    amura
    -0.07
    uhl
    -0.07
    ieber
    -0.06
    bras
    -0.06
    264
    -0.06
    964
    -0.06
    agli
    -0.06
    pty
    -0.06
    _void
    -0.06
    iams
    -0.06
    POSITIVE LOGITS
    西çľģ
    0.07
    longleftrightarrow
    0.07
     Voy
    0.06
     fm
    0.06
    alion
    0.06
    <Scalar
    0.06
    fds
    0.06
    ROTO
    0.06
     courage
    0.06
    kiye
    0.06
    Activations Density 0.009%

    No Known Activations