© 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. 15-LLAMASCOPE-RES-131K
    11. 791
    Prev
    Next
    INDEX
    Explanations

    instances of personal pronouns indicating the speaker's experiences and actions

    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
     itself
    -0.07
    éĢļãĤĬ
    -0.06
    .Dao
    -0.06
     _
    -0.06
     beri
    -0.06
    f
    -0.06
    pedia
    -0.06
    bÃŃr
    -0.06
    eyer
    -0.06
     Quentin
    -0.06
    POSITIVE LOGITS
     alike
    0.09
    zelf
    0.07
    embros
    0.07
    ppers
    0.07
    xious
    0.07
    quals
    0.06
    aukee
    0.06
    دÛĮگر
    0.06
    ainen
    0.06
    istr
    0.06
    Activations Density 0.007%

    No Known Activations