© 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. 9-LLAMASCOPE-RES-131K
    11. 94505
    Prev
    Next
    INDEX
    Explanations

    conversational markers and expressions of sentiment

    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
    lee
    -0.06
     ```
    -0.06
    иÑģÑĤÑĢа
    -0.06
    erli
    -0.05
     caution
    -0.05
    öm
    -0.05
     dashes
    -0.05
    095
    -0.05
     dash
    -0.05
     deleg
    -0.05
    POSITIVE LOGITS
     ná»ģn
    0.07
     SCIP
    0.07
    ONUS
    0.07
    enton
    0.07
    Ú¯ÙĪÛĮ
    0.07
    VOKE
    0.07
    -caret
    0.07
    åģ¥
    0.07
    ırak
    0.07
    wig
    0.06
    Activations Density 0.009%

    No Known Activations