© 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. 9-LLAMASCOPE-RES-131K
    11. 95895
    Prev
    Next
    INDEX
    Explanations

    programming language syntax elements, particularly method signatures and return statements

    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
    leys
    -0.06
    issan
    -0.06
    abolic
    -0.06
    lags
    -0.06
    iti
    -0.06
    ovny
    -0.06
    oton
    -0.06
     congr
    -0.06
    eton
    -0.06
    icho
    -0.06
    POSITIVE LOGITS
    HLT
    0.09
    ulado
    0.07
    atest
    0.07
     Dudley
    0.07
    ainless
    0.07
    åħ
    0.06
    éŃĤ
    0.06
     Lum
    0.06
    инкÑĥ
    0.06
    .GroupLayout
    0.06
    Activations Density 0.002%

    No Known Activations