© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 74729
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods

    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
    pars
    -0.06
    imony
    -0.06
     beg
    -0.06
    nun
    -0.06
    imd
    -0.06
    é¨
    -0.06
    tempt
    -0.06
     Beg
    -0.06
     Vibr
    -0.06
     GE
    -0.06
    POSITIVE LOGITS
    istas
    0.07
    ista
    0.07
     conting
    0.06
    Ø¡
    0.06
    hek
    0.06
    spark
    0.06
    urb
    0.06
    otec
    0.06
    avn
    0.06
    110
    0.06
    Activations Density 0.002%

    No Known Activations