© 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. 88740
    Prev
    Next
    INDEX
    Explanations

    punctuation, specifically commas

    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
     Kens
    -0.07
    aid
    -0.07
    azz
    -0.06
    -0.06
    ographic
    -0.06
    èijĹ
    -0.06
    aida
    -0.06
    lesi
    -0.06
     cowork
    -0.06
     Noble
    -0.06
    POSITIVE LOGITS
     moi
    0.08
    ESSAGES
    0.07
    IFF
    0.07
    -plus
    0.07
    _FF
    0.07
     пÑĢид
    0.07
    plus
    0.07
    ertino
    0.06
     emot
    0.06
    ETY
    0.06
    Activations Density 0.000%

    No Known Activations