© 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 EvalsExportsAPI 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. 58663
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and dashes in text

    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
    оÑģÑĢед
    -0.07
    ÂŃs
    -0.07
    ains
    -0.07
    antz
    -0.07
    ROUND
    -0.07
    ults
    -0.06
    áb
    -0.06
    IJ
    -0.06
    ais
    -0.06
     Kimberly
    -0.06
    POSITIVE LOGITS
    ÑĢовиÑĩ
    0.07
     BaÄŁ
    0.06
    AUTHORIZED
    0.06
    죽
    0.06
     dÆ°Æ¡ng
    0.06
    âĶģ
    0.06
    umlu
    0.06
     Chargers
    0.06
     ########.
    0.06
    ovic
    0.06
    Activations Density 0.002%

    No Known Activations