© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 126405
    Prev
    Next
    INDEX
    Explanations

    conditional assertions and debugging checks 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
     slightest
    -0.06
    å¿Ĺ
    -0.06
     Blanc
    -0.06
    voje
    -0.06
    curring
    -0.06
    èĬĿ
    -0.06
     usleep
    -0.06
    linkplain
    -0.06
    ÑĢик
    -0.06
    iesen
    -0.06
    POSITIVE LOGITS
    emachine
    0.07
     forb
    0.06
    ament
    0.06
    rames
    0.06
    eria
    0.06
     morphology
    0.06
    .navigationItem
    0.06
    ãĥĥãĤ·ãĥ¥
    0.06
    /problems
    0.06
    morph
    0.06
    Activations Density 0.007%

    No Known Activations