© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 125239
    Prev
    Next
    INDEX
    Explanations

    the presence of annotations or documentation comments 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
     ind
    -0.08
    dorf
    -0.07
    alli
    -0.07
     Dank
    -0.06
    ooke
    -0.06
    fern
    -0.06
    oy
    -0.06
     cor
    -0.06
     accord
    -0.06
    stm
    -0.06
    POSITIVE LOGITS
    veau
    0.08
    utsch
    0.07
    uce
    0.07
    .generator
    0.06
    877
    0.06
    ickle
    0.06
    ombine
    0.06
    uada
    0.06
    -fw
    0.06
     upset
    0.06
    Activations Density 0.002%

    No Known Activations