© 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. 71516
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and career aspirations

    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
    eldom
    -0.09
    leo
    -0.06
    uro
    -0.06
     premiere
    -0.06
    alon
    -0.06
     Yesterday
    -0.06
    eln
    -0.06
     pent
    -0.06
    etu
    -0.06
    pent
    -0.06
    POSITIVE LOGITS
    933
    0.07
    swire
    0.07
    ÏĥÏĦη
    0.07
     Chow
    0.07
     rozhod
    0.06
    OUNT
    0.06
     prostitutas
    0.06
    γκÏĮ
    0.06
    zeichnet
    0.06
     ê²°ìłķ
    0.06
    Activations Density 0.011%

    No Known Activations