© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 71209
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditional situations or scenarios

    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
    GENCY
    -0.07
    ردÙĩ
    -0.06
    ographics
    -0.06
    ManagedObjectContext
    -0.06
     youre
    -0.06
     Twice
    -0.06
     Duck
    -0.06
    ÏĢλα
    -0.06
    .mybatisplus
    -0.06
     twice
    -0.06
    POSITIVE LOGITS
     ultimately
    0.09
     somehow
    0.08
     eventually
    0.08
     tomorrow
    0.07
    arb
    0.07
     indeed
    0.07
     turnout
    0.07
    mina
    0.07
    ël
    0.07
     outcome
    0.07
    Activations Density 0.030%

    No Known Activations