© 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. 85025
    Prev
    Next
    INDEX
    Explanations

    specific technical functions and operations related to programming or data processing

    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
    angi
    -0.08
    uya
    -0.07
    eral
    -0.07
     ucwords
    -0.07
     len
    -0.07
     ng
    -0.07
    ross
    -0.06
     Griff
    -0.06
    iap
    -0.06
     Hen
    -0.06
    POSITIVE LOGITS
     array
    0.08
    cisi
    0.08
    živ
    0.07
    oner
    0.07
     rewind
    0.07
    .Abstractions
    0.07
    ibase
    0.07
    deaux
    0.07
    acas
    0.07
    йн
    0.07
    Activations Density 0.077%

    No Known Activations