© 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. 31271
    Prev
    Next
    INDEX
    Explanations

    open and close parentheses in code-related contexts

    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
    амеÑĤ
    -0.07
    iously
    -0.07
    ccione
    -0.07
    иÑģÑģ
    -0.07
    hower
    -0.07
    pom
    -0.07
    enerator
    -0.07
    _observer
    -0.07
    stro
    -0.07
    ão
    -0.07
    POSITIVE LOGITS
    ona
    0.06
    ANTITY
    0.06
    es
    0.06
    je
    0.05
    zure
    0.05
    321
    0.05
    ATTR
    0.05
    377
    0.05
    _attrs
    0.05
     Rav
    0.05
    Activations Density 0.001%

    No Known Activations