© 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. 121088
    Prev
    Next
    INDEX
    Explanations

    various forms of punctuation and document structure

    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
     Dün
    -0.07
    PÅĻÃŃ
    -0.07
     é©
    -0.07
     merk
    -0.07
    >//
    -0.07
    -mf
    -0.06
    ávÄĽ
    -0.06
    wu
    -0.06
    taÅŁ
    -0.06
    peg
    -0.06
    POSITIVE LOGITS
    201
    0.11
    199
    0.09
    200
    0.09
    198
    0.08
    rowsable
    0.08
    196
    0.08
    197
    0.07
    195
    0.07
    одÑĭ
    0.07
    202
    0.07
    Activations Density 0.011%

    No Known Activations