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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 62112
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords, specifically function and visibility modifiers

    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
    iali
    -0.07
    ereum
    -0.07
    .***.***
    -0.07
    resse
    -0.07
    akis
    -0.07
    iaux
    -0.07
     Kür
    -0.06
    ystone
    -0.06
    ngth
    -0.06
     circumstance
    -0.06
    POSITIVE LOGITS
    arin
    0.07
    cess
    0.06
    nder
    0.06
    eer
    0.06
     Mason
    0.06
    uhan
    0.06
     neutrality
    0.06
    iffs
    0.06
    osal
    0.06
    ferred
    0.06
    Activations Density 0.000%

    No Known Activations