© 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. 84442
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics

    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
    aths
    -0.07
    iasi
    -0.07
    flen
    -0.07
    رÙĩ
    -0.07
    nze
    -0.07
    abee
    -0.07
    ARSE
    -0.07
    ÑĦа
    -0.06
    iqueta
    -0.06
    ÃŃg
    -0.06
    POSITIVE LOGITS
    ãĥĥ
    0.06
     Hiring
    0.06
     hires
    0.06
    rides
    0.06
    edly
    0.06
     Wyn
    0.06
     schedules
    0.06
    305
    0.05
    TRL
    0.05
     Nex
    0.05
    Activations Density 0.001%

    No Known Activations