© 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. 27136
    Prev
    Next
    INDEX
    Explanations

    questions related to length, time, species, hierarchy, and general inquiries

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

    Question phrases that begin standard information-seeking queries, typically starting with question words (how, what, who, where) followed by auxiliary verbs or main verbs.

    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
    .Networking
    -0.06
    fter
    -0.06
     Shin
    -0.06
    /**↵↵
    -0.06
    окол
    -0.06
    ãĢ
    -0.06
    perl
    -0.06
     sce
    -0.06
     XXX
    -0.06
     Alphabet
    -0.06
    POSITIVE LOGITS
    outu
    0.06
     onDataChange
    0.06
    patch
    0.06
    Edit
    0.06
    508
    0.06
    urdy
    0.06
    icorn
    0.06
     PureComponent
    0.06
    allah
    0.06
    ÂŃtion
    0.06
    Activations Density 0.069%

    No Known Activations