© 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. 107197
    Prev
    Next
    INDEX
    Explanations

    figures and equations referenced in the document

    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
    бо
    -0.07
    ór
    -0.07
    384
    -0.07
     strSQL
    -0.07
    affen
    -0.06
    pez
    -0.06
    amo
    -0.06
    šak
    -0.06
    моÑĢ
    -0.06
     án
    -0.06
    POSITIVE LOGITS
    itol
    0.08
    aturdays
    0.07
    gett
    0.07
    olicit
    0.07
    zech
    0.07
    arcy
    0.06
    issen
    0.06
    indsay
    0.06
    atel
    0.06
    CGSize
    0.06
    Activations Density 0.118%

    No Known Activations