© 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. 91904
    Prev
    Next
    INDEX
    Explanations

    information related to personal details and statistics about individuals

    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
    egl
    -0.07
    auc
    -0.07
    azole
    -0.07
    PUTE
    -0.07
    entine
    -0.07
    icode
    -0.07
    ergy
    -0.07
    ibold
    -0.07
    eteria
    -0.07
    agr
    -0.06
    POSITIVE LOGITS
    [email
    0.07
    1
    0.06
     flo
    0.06
     Roo
    0.06
    kich
    0.06
     otherwise
    0.06
    555
    0.05
     Canter
    0.05
    otherwise
    0.05
    ellular
    0.05
    Activations Density 0.002%

    No Known Activations