© 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 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. 130781
    Prev
    Next
    INDEX
    Explanations

    instances of function declarations 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
    $MESS
    -0.08
    emachine
    -0.08
    mlx
    -0.08
    elan
    -0.08
    ãĤĭ
    -0.08
    pus
    -0.07
    imitives
    -0.07
    odont
    -0.07
     .|
    -0.07
    æķµ
    -0.07
    POSITIVE LOGITS
     finally
    0.07
    (err
    0.06
     error
    0.06
    942
    0.06
     w
    0.06
    076
    0.06
    era
    0.05
    w
    0.05
    _
    0.05
    ILD
    0.05
    Activations Density 0.002%

    No Known Activations