© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 85201
    Prev
    Next
    INDEX
    Explanations

    references to academic citations and authorship

    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
    ivas
    -0.07
    ÄĽnÃŃ
    -0.06
    adio
    -0.06
    icz
    -0.06
    460
    -0.06
    haar
    -0.06
    ivot
    -0.06
    "crypto
    -0.06
    azzo
    -0.06
    esan
    -0.06
    POSITIVE LOGITS
    ège
    0.10
    tle
    0.07
    วม
    0.07
    Äįas
    0.07
    aby
    0.07
    ervo
    0.07
    itar
    0.07
    érique
    0.06
    oma
    0.06
    ngen
    0.06
    Activations Density 0.008%

    No Known Activations