© 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. 40248
    Prev
    Next
    INDEX
    Explanations

    instances of the word "many," indicating a focus on quantification or the prevalence of something

    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
    ť
    -0.07
    cern
    -0.07
    stown
    -0.07
    pers
    -0.07
    çļĦæĥħ
    -0.06
    sumer
    -0.06
    åİŁå§ĭ
    -0.06
    ogene
    -0.06
    igo
    -0.06
    GI
    -0.06
    POSITIVE LOGITS
     times
    0.11
    /how
    0.10
    /all
    0.08
    /if
    0.08
    -times
    0.08
    times
    0.07
     other
    0.07
     people
    0.07
     different
    0.06
     veces
    0.06
    Activations Density 0.005%

    No Known Activations