© 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. 82110
    Prev
    Next
    INDEX
    Explanations

    calls to action or encouragement towards specific behaviors or activities

    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
     Ston
    -0.07
    gu
    -0.07
    Ìĥ
    -0.06
    elist
    -0.06
    gm
    -0.06
    lov
    -0.06
    rek
    -0.06
    åĩ¦
    -0.06
    alt
    -0.05
    enes
    -0.05
    POSITIVE LOGITS
    :č↵č↵
    0.08
     everyone
    0.07
    munition
    0.07
    igham
    0.07
    eroon
    0.07
    endas
    0.07
    hoa
    0.07
    partner
    0.07
    igits
    0.06
    ">//
    0.06
    Activations Density 0.007%

    No Known Activations