© 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. 95014
    Prev
    Next
    INDEX
    Explanations

    programming-related actions or concepts involving data manipulation and management

    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
    (s
    -0.07
    sl
    -0.07
    ãģŁãĤī
    -0.06
    els
    -0.06
    åıĬåħ¶
    -0.06
    otec
    -0.06
     Cob
    -0.06
    ↵
    -0.06
    ds
    -0.06
    re
    -0.06
    POSITIVE LOGITS
    /***/
    0.08
     them
    0.08
    ábado
    0.07
    jÃł
    0.07
    assis
    0.07
    formats
    0.07
    .AutoSizeMode
    0.07
    ..↵↵↵↵
    0.07
    gın
    0.07
     this
    0.06
    Activations Density 0.076%

    No Known Activations