© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 99009
    Prev
    Next
    INDEX
    Explanations

    punctuations, line breaks, and structural elements in text

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    rat
    -0.06
    OOT
    -0.06
    ulo
    -0.06
     peripheral
    -0.05
    íĻĶ
    -0.05
    BaseContext
    -0.05
    103
    -0.05
    avian
    -0.05
    -pro
    -0.05
    èĴĤ
    -0.05
    POSITIVE LOGITS
    grese
    0.07
    iddi
    0.07
    áºŃt
    0.07
    mlin
    0.07
    Ñijм
    0.07
    nesc
    0.07
    andin
    0.07
    ehr
    0.07
    ccd
    0.07
    à¸Ķา
    0.06
    Activations Density 0.030%

    No Known Activations