© 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. 9-LLAMASCOPE-RES-131K
    11. 94410
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and imports from various coding languages

    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
    ileo
    -0.06
     PMC
    -0.06
    StackTrace
    -0.06
    uku
    -0.06
    SHOT
    -0.06
     DIM
    -0.06
     Vent
    -0.06
    lam
    -0.06
    leans
    -0.06
    .dispose
    -0.06
    POSITIVE LOGITS
     RequestContext
    0.07
    WithContext
    0.06
    phalt
    0.06
    adf
    0.06
    quiv
    0.06
    egrator
    0.06
     likely
    0.06
    ona
    0.06
    addir
    0.06
    _HAL
    0.06
    Activations Density 0.001%

    No Known Activations