© 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. 28481
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names associated with individuals, locations, and organizations

    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
    [email
    -0.07
     Void
    -0.07
     ev
    -0.07
     ï
    -0.07
    ạo
    -0.07
    ฺ
    -0.06
    yal
    -0.06
    baru
    -0.06
     Prostit
    -0.06
     Dear
    -0.06
    POSITIVE LOGITS
     itself
    0.10
    ฯ
    0.07
    gar
    0.06
    acci
    0.06
    sson
    0.06
    plies
    0.06
    ifa
    0.06
    propri
    0.06
     afore
    0.06
     herself
    0.06
    Activations Density 0.041%

    No Known Activations