© 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. 53750
    Prev
    Next
    INDEX
    Explanations

    mathematical constructs and properties related to functions, sets, and sequences

    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
    leyen
    -0.08
    odyn
    -0.07
    ledik
    -0.06
     donn
    -0.06
    aign
    -0.06
    ÐŁÐ¾Ñģ
    -0.06
    _EXTENDED
    -0.06
    _lite
    -0.06
    ادÙĨ
    -0.06
     Odds
    -0.06
    POSITIVE LOGITS
     whose
    0.07
    ValuePair
    0.07
    YP
    0.07
    enso
    0.07
    .Debugger
    0.07
    opa
    0.07
     dass
    0.06
     że
    0.06
    ential
    0.06
     multiplier
    0.06
    Activations Density 0.076%

    No Known Activations