© 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. 105407
    Prev
    Next
    INDEX
    Explanations

    syntactical elements and punctuations 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
    _QMARK
    -0.07
    &action
    -0.07
    ضÙĪ
    -0.07
    eft
    -0.07
    anness
    -0.07
    auses
    -0.07
     ucwords
    -0.07
    Helvetica
    -0.06
    POCH
    -0.06
    Specifier
    -0.06
    POSITIVE LOGITS
    ou
    0.07
    py
    0.07
     âĸ²
    0.07
     py
    0.06
    inia
    0.06
    ith
    0.06
    umper
    0.06
     masses
    0.06
    prime
    0.06
    PY
    0.06
    Activations Density 0.014%

    No Known Activations