© 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. 126427
    Prev
    Next
    INDEX
    Explanations

    programming-related commands and expressions

    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
    ulp
    -0.08
    raq
    -0.08
    ibern
    -0.07
    kul
    -0.07
    openh
    -0.07
    avel
    -0.07
    ietf
    -0.07
    agal
    -0.07
    abwe
    -0.07
    ULE
    -0.07
    POSITIVE LOGITS
     Bour
    0.07
    trap
    0.07
    cape
    0.06
     Bash
    0.06
     sh
    0.06
     FOOT
    0.06
    ãĤ·ãĥ§
    0.06
     traps
    0.06
     touch
    0.06
     McGr
    0.06
    Activations Density 0.000%

    No Known Activations