© 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. 30296
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax elements and constructs

    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
     Fa
    -0.06
     cir
    -0.06
    _RW
    -0.06
     fa
    -0.06
     sav
    -0.05
    edral
    -0.05
     Rud
    -0.05
     circ
    -0.05
    OV
    -0.05
    escal
    -0.05
    POSITIVE LOGITS
     count
    0.11
     size
    0.10
     getCount
    0.10
    .size
    0.10
    size
    0.09
    len
    0.09
     itemCount
    0.09
    .count
    0.09
     Len
    0.09
    SIZE
    0.09
    Activations Density 0.033%

    No Known Activations