© 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. 3756
    Prev
    Next
    INDEX
    Explanations

    dynamic actions and movements in narratives

    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
     permanently
    -0.06
    cu
    -0.06
     ro
    -0.06
    ovic
    -0.06
     liken
    -0.05
    .trace
    -0.05
     temporarily
    -0.05
    ves
    -0.05
    odore
    -0.05
    ies
    -0.05
    POSITIVE LOGITS
    .eng
    0.08
    ãĤ¤ãĥĦ
    0.08
    Ymd
    0.07
    velope
    0.07
     itself
    0.07
    Ļ
    0.07
    pite
    0.07
    dÄĽ
    0.07
    /meta
    0.07
    vod
    0.07
    Activations Density 0.042%

    No Known Activations