© 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. 74182
    Prev
    Next
    INDEX
    Explanations

    punctuation and numerical data

    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
    dent
    -0.07
    aina
    -0.07
    lage
    -0.07
    SED
    -0.06
    avel
    -0.06
    erdale
    -0.06
    .setter
    -0.06
    occo
    -0.06
    doch
    -0.06
    oxy
    -0.06
    POSITIVE LOGITS
     temperature
    0.08
     Temperature
    0.07
     temperatures
    0.07
    Temperature
    0.06
    _SENS
    0.06
    temperature
    0.06
    à¸Ĺร
    0.06
    ÛĢ
    0.06
    inz
    0.06
     Sle
    0.06
    Activations Density 0.002%

    No Known Activations