© 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. 15-LLAMASCOPE-RES-131K
    11. 61621
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and variables

    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
    yre
    -0.08
    é½
    -0.08
    icros
    -0.08
    inç
    -0.08
     bordel
    -0.07
    yne
    -0.07
    ialis
    -0.07
    roperties
    -0.07
    ensex
    -0.07
    esser
    -0.07
    POSITIVE LOGITS
     sh
    0.07
     Feinstein
    0.07
    eron
    0.06
     wh
    0.06
     rel
    0.06
    614
    0.06
    å¡
    0.06
    802
    0.06
     t
    0.05
    whelming
    0.05
    Activations Density 0.004%

    No Known Activations