© 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. 92124
    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
    _locals
    -0.06
    دÙĩÙħ
    -0.06
     gap
    -0.06
     reluct
    -0.06
    .Lookup
    -0.06
    ware
    -0.06
    Statics
    -0.05
     каж
    -0.05
    _helpers
    -0.05
    ãģŁãĤī
    -0.05
    POSITIVE LOGITS
    hoff
    0.08
    kea
    0.08
    kees
    0.07
     Rig
    0.07
     IDb
    0.07
    arrera
    0.06
    -scrollbar
    0.06
    bens
    0.06
    yro
    0.06
    olec
    0.06
    Activations Density 0.000%

    No Known Activations