© 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. 26829
    Prev
    Next
    INDEX
    Explanations

    patterns in programming syntax related to function definitions and control structures

    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
    arel
    -0.07
    릿
    -0.07
     [[]
    -0.06
    áp
    -0.06
     èİ
    -0.06
    ÅĻet
    -0.05
    oyo
    -0.05
    ÙĦÙģ
    -0.05
    jÃŃt
    -0.05
    elo
    -0.05
    POSITIVE LOGITS
    .gdx
    0.07
    ê
    0.07
    haul
    0.07
    hoe
    0.07
    zin
    0.07
    missive
    0.07
    enie
    0.07
    tej
    0.07
    illard
    0.06
    otland
    0.06
    Activations Density 0.035%

    No Known Activations