© 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. 105409
    Prev
    Next
    INDEX
    Explanations

    punctuation marks in a narrative

    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
    754
    -0.07
     fucking
    -0.07
    å±ı
    -0.06
     shit
    -0.06
     fuck
    -0.06
    787
    -0.06
    757
    -0.06
     shitty
    -0.06
    Advertisements
    -0.06
    .environment
    -0.06
    POSITIVE LOGITS
    rodu
    0.07
    ãĥ³ãĥĩ
    0.07
    eway
    0.07
    util
    0.06
     déjÃł
    0.06
     spos
    0.06
     razor
    0.06
    ignum
    0.06
    eor
    0.06
    _MALLOC
    0.06
    Activations Density 0.000%

    No Known Activations