© 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. 22-LLAMASCOPE-RES-131K
    11. 4208
    Prev
    Next
    INDEX
    Explanations

    expressions of doubt or loss of certainty regarding identity or authority

    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
    renom
    -0.07
    aru
    -0.07
    svp
    -0.07
    749
    -0.07
    avia
    -0.07
    اÙĪت
    -0.07
    adia
    -0.07
    erb
    -0.07
    ointment
    -0.07
    اجات
    -0.07
    POSITIVE LOGITS
     lose
    0.31
     losing
    0.29
     loss
    0.27
     loses
    0.27
     lost
    0.27
     Lose
    0.25
     Loss
    0.24
    losing
    0.23
    loss
    0.23
    lose
    0.23
    Activations Density 0.058%

    No Known Activations