© 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. 3795
    Prev
    Next
    INDEX
    Explanations

    references to standards, specifications, or conditions related to age and qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text fragments that involve meta-discussions about language, linguistic clarifications, definitions, or translations between different writing systems.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    lei
    -0.07
    ág
    -0.07
    áº
    -0.06
    imi
    -0.06
    THON
    -0.06
     BASIS
    -0.06
    Reader
    -0.06
    790
    -0.06
     primal
    -0.06
     Reader
    -0.06
    POSITIVE LOGITS
    exion
    0.06
    preter
    0.06
     passe
    0.06
    -utils
    0.06
    599
    0.06
    ÑĪÑĤов
    0.06
     English
    0.06
     usage
    0.06
    Rew
    0.06
     ÑĥпоÑĤÑĢеб
    0.06
    Activations Density 0.008%

    No Known Activations