© 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. 104745
    Prev
    Next
    INDEX
    Explanations

    terms associated with multimedia releases and production details

    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
    zet
    -0.07
    Ī
    -0.06
    indr
    -0.06
     pers
    -0.06
     Hud
    -0.06
    fleet
    -0.06
     opposite
    -0.06
    بات
    -0.05
    oi
    -0.05
     pic
    -0.05
    POSITIVE LOGITS
    ccione
    0.07
    vos
    0.07
    ëĬ
    0.07
     Everywhere
    0.07
    rowsable
    0.07
    nowrap
    0.07
    zeÅĦ
    0.07
    ichtig
    0.07
    opsis
    0.07
    abbo
    0.06
    Activations Density 0.003%

    No Known Activations