© 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. 92443
    Prev
    Next
    INDEX
    Explanations

    sentences that convey uncertainty or speculation about the future

    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
    avern
    -0.07
    fi
    -0.07
     Demon
    -0.07
    ayload
    -0.07
    bjerg
    -0.06
     Cumhur
    -0.06
    indr
    -0.06
    ippi
    -0.06
     Haram
    -0.06
     cres
    -0.06
    POSITIVE LOGITS
    udas
    0.06
    etri
    0.06
    atri
    0.06
    -parameter
    0.05
     xe
    0.05
    aine
    0.05
     takım
    0.05
    çĽ£çĿ£
    0.05
     EW
    0.05
    mouseup
    0.05
    Activations Density 0.062%

    No Known Activations