© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 72360
    Prev
    Next
    INDEX
    Explanations

    instances of function return statements in programming 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
    ged
    -0.08
    ging
    -0.08
    iasi
    -0.07
    gle
    -0.07
    out
    -0.07
     rarity
    -0.07
    èµ·æĿ¥
    -0.07
    uality
    -0.06
    го
    -0.06
    pare
    -0.06
    POSITIVE LOGITS
    ees
    0.10
    swire
    0.08
    .Reporting
    0.08
    _sequences
    0.08
    edException
    0.08
    /Edit
    0.08
    (Return
    0.07
    íĶĪ
    0.07
    ansom
    0.07
    aldo
    0.07
    Activations Density 0.040%

    No Known Activations