© 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. 69661
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the protection or confidentiality of personal information

    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
    chen
    -0.06
    amon
    -0.06
    cre
    -0.06
    omo
    -0.06
    uco
    -0.06
    omi
    -0.06
    itchen
    -0.06
    rawer
    -0.06
    oric
    -0.06
    ce
    -0.05
    POSITIVE LOGITS
    vez
    0.07
    ữ
    0.07
    vé
    0.07
    Å¡ak
    0.06
    ujet
    0.06
     RETURN
    0.06
     strict
    0.06
     Fem
    0.06
     wes
    0.06
    çak
    0.06
    Activations Density 0.000%

    No Known Activations