© 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. 116909
    Prev
    Next
    INDEX
    Explanations

    code-related constructs and syntax in programming 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
    uco
    -0.08
     fidelity
    -0.07
    ijkstra
    -0.06
    ınca
    -0.06
    549
    -0.06
     ÚĨÛĮÙĨ
    -0.06
    bool
    -0.06
     Verm
    -0.06
    ãģĸ
    -0.06
    _inverse
    -0.06
    POSITIVE LOGITS
    ikk
    0.07
    -reset
    0.06
     PR
    0.06
    arel
    0.06
     integer
    0.06
    ogen
    0.06
    PR
    0.06
    borg
    0.06
    GeneratedValue
    0.06
    quences
    0.06
    Activations Density 0.001%

    No Known Activations