© 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. 130093
    Prev
    Next
    INDEX
    Explanations

    references to pagination or indexing in text

    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
    arendra
    -0.07
    lá
    -0.07
    岡
    -0.06
    jie
    -0.06
    atism
    -0.06
    å¦ĥ
    -0.06
    eties
    -0.06
    nger
    -0.06
    梨
    -0.06
    zac
    -0.06
    POSITIVE LOGITS
     opp
    0.06
     dedic
    0.06
    paged
    0.06
     front
    0.06
    enance
    0.06
    /main
    0.06
    oph
    0.06
    front
    0.06
    oon
    0.06
     priority
    0.06
    Activations Density 0.002%

    No Known Activations