© 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. 124834
    Prev
    Next
    INDEX
    Explanations

    references to file names and their manipulations in code

    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
    izi
    -0.07
    NESS
    -0.07
    een
    -0.07
    atee
    -0.07
    headed
    -0.07
    umbs
    -0.07
    rey
    -0.07
    &view
    -0.06
    gui
    -0.06
    -ÑĤаки
    -0.06
    POSITIVE LOGITS
    plate
    0.09
    plates
    0.08
    ake
    0.08
    /filepath
    0.08
    ervers
    0.07
    akes
    0.07
    cke
    0.07
    paces
    0.07
    apyrus
    0.07
    erule
    0.07
    Activations Density 0.009%

    No Known Activations