© 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. 87149
    Prev
    Next
    INDEX
    Explanations

    technical keywords related to data structures and scripting

    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
    imen
    -0.07
    fty
    -0.07
     vrou
    -0.06
    erna
    -0.06
     window
    -0.06
    .Stage
    -0.06
    .stage
    -0.06
    ril
    -0.05
    digest
    -0.05
    pine
    -0.05
    POSITIVE LOGITS
     <!--[
    0.08
    çĿ
    0.08
    (sheet
    0.07
     sheet
    0.07
    .usermodel
    0.07
    PHPExcel
    0.07
     Sheet
    0.07
    ç½
    0.07
    ENCED
    0.07
     MetroFramework
    0.07
    Activations Density 0.005%

    No Known Activations