© 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. 121004
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting peculiarities in a programming context

    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
    swire
    -0.07
     decom
    -0.07
    latable
    -0.07
    ichert
    -0.07
     slik
    -0.07
    hlas
    -0.06
    emade
    -0.06
    rien
    -0.06
    htar
    -0.06
    utton
    -0.06
    POSITIVE LOGITS
    ERAL
    0.06
    èĪ
    0.06
    ParameterValue
    0.06
    TAG
    0.06
    ombre
    0.06
    omy
    0.06
    classpath
    0.06
    Wildcard
    0.06
    utivo
    0.06
     Byl
    0.06
    Activations Density 0.011%

    No Known Activations