© 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. 17-LLAMASCOPE-RES-131K
    11. 80545
    Prev
    Next
    INDEX
    Explanations

    specific punctuation and formatting elements 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
    ियत
    -0.07
    bourg
    -0.07
    ndo
    -0.07
    един
    -0.07
    adt
    -0.07
    tram
    -0.07
    abee
    -0.07
    _DIP
    -0.06
    rang
    -0.06
    conc
    -0.06
    POSITIVE LOGITS
     Stable
    0.06
    uar
    0.05
    âķ
    0.05
    up
    0.05
     sefer
    0.05
    SIG
    0.05
    .foundation
    0.05
    लब
    0.05
    Tro
    0.05
    _RSA
    0.05
    Activations Density 0.001%

    No Known Activations