© 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. 9-LLAMASCOPE-RES-131K
    11. 95906
    Prev
    Next
    INDEX
    Explanations

    references to subsequent developments or proofs in scientific discussions

    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
     straw
    -0.07
    ascar
    -0.06
    ivor
    -0.06
     decom
    -0.05
    eryl
    -0.05
     grass
    -0.05
    oppel
    -0.05
     screw
    -0.05
    ô
    -0.05
     dest
    -0.05
    POSITIVE LOGITS
    oldt
    0.08
    .xhtml
    0.08
    rava
    0.08
    aterangepicker
    0.07
     later
    0.07
     имÑĥ
    0.07
    ÑĢÑİ
    0.07
    ofile
    0.07
    cce
    0.07
    elters
    0.07
    Activations Density 0.023%

    No Known Activations