© 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. 106989
    Prev
    Next
    INDEX
    Explanations

    references to personal events and activities in a narrative context

    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
    ÑĥлÑİ
    -0.07
    ilar
    -0.07
    iedo
    -0.07
    Assignable
    -0.07
    å¯
    -0.07
    .telegram
    -0.07
    ["$
    -0.07
    OPS
    -0.06
    .define
    -0.06
    znám
    -0.06
    POSITIVE LOGITS
     tomorrow
    0.07
     school
    0.06
    nex
    0.06
     orientations
    0.06
     birthday
    0.06
     Consumer
    0.06
    adh
    0.06
    eling
    0.06
     birthdays
    0.06
    isse
    0.05
    Activations Density 0.034%

    No Known Activations