© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 104457
    Prev
    Next
    INDEX
    Explanations

    opening curly braces in the 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
     Kurd
    -0.07
    $MESS
    -0.06
     Alg
    -0.06
    оÑĢÑĸв
    -0.06
    AGIC
    -0.06
    æĢ¥
    -0.06
    á»ģn
    -0.06
    aleb
    -0.06
    agnosis
    -0.06
    zte
    -0.06
    POSITIVE LOGITS
    hythm
    0.07
    isas
    0.07
    amentos
    0.06
    ocal
    0.06
    ington
    0.06
    iales
    0.06
    gart
    0.06
    ouchers
    0.06
    uj
    0.06
    icare
    0.06
    Activations Density 0.000%

    No Known Activations