© 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. 72384
    Prev
    Next
    INDEX
    Explanations

    sentences with emotional or contemplative punctuation

    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
    Propagation
    -0.07
    onna
    -0.07
    _Speed
    -0.07
    ctor
    -0.07
    zet
    -0.07
    /tiny
    -0.07
    .thumb
    -0.07
    еÑĢи
    -0.07
    unsch
    -0.07
    olvers
    -0.07
    POSITIVE LOGITS
    chner
    0.07
    licit
    0.06
    cape
    0.06
     éŁĵ
    0.06
     till
    0.05
    olini
    0.05
     whose
    0.05
    nodoc
    0.05
      ↵
    0.05
     than
    0.05
    Activations Density 0.022%

    No Known Activations