© 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. 17-LLAMASCOPE-RES-131K
    11. 125095
    Prev
    Next
    INDEX
    Explanations

    instances of technical or formal documentation identifiers

    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
    avourite
    -0.05
     rental
    -0.05
    olph
    -0.05
    estre
    -0.05
     Rental
    -0.05
    elp
    -0.05
    olt
    -0.05
    ostel
    -0.05
     colourful
    -0.05
    icari
    -0.05
    POSITIVE LOGITS
    511
    0.07
    outu
    0.07
    롤
    0.07
    iore
    0.07
     migrationBuilder
    0.07
    ActionCreators
    0.06
    åĿĬ
    0.06
     creampie
    0.06
    abic
    0.06
    oppins
    0.06
    Activations Density 0.000%

    No Known Activations