© 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. 62361
    Prev
    Next
    INDEX
    Explanations

    punctuation and question marks

    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
    Hunter
    -0.07
     deser
    -0.06
     tribute
    -0.06
    land
    -0.06
     ar
    -0.06
    esa
    -0.06
     superheroes
    -0.06
     Hunter
    -0.06
     Scratch
    -0.06
     chase
    -0.06
    POSITIVE LOGITS
    elik
    0.08
    acin
    0.07
    ansi
    0.07
    ela
    0.07
    ansom
    0.06
    ality
    0.06
    POSIT
    0.06
    ê·ł
    0.06
     Cust
    0.06
     Shapiro
    0.06
    Activations Density 0.002%

    No Known Activations