© 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. 3714
    Prev
    Next
    INDEX
    Explanations

    section numbers or references typically used in academic papers

    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
    anca
    -0.07
    irit
    -0.07
    inium
    -0.07
    unger
    -0.07
    empl
    -0.07
    ãĥ¬ãĥĥãĥĪ
    -0.06
    loom
    -0.06
    edium
    -0.06
    á»ĭ
    -0.06
    DataReader
    -0.06
    POSITIVE LOGITS
    SG
    0.06
    jets
    0.06
    ήÏĤ
    0.06
    ourced
    0.06
     luder
    0.06
    Tap
    0.06
    ADIUS
    0.06
     çİ©
    0.06
     Carlson
    0.06
     gir
    0.05
    Activations Density 0.000%

    No Known Activations