© 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. 28956
    Prev
    Next
    INDEX
    Explanations

    instances of self-referential pronouns and expressions

    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
    ixe
    -0.07
    ysa
    -0.07
    ichern
    -0.07
    flies
    -0.07
     jadx
    -0.07
    nev
    -0.06
    obia
    -0.06
    decess
    -0.06
    SQ
    -0.06
    ëĬIJ
    -0.06
    POSITIVE LOGITS
     hereby
    0.07
     minus
    0.06
    ÉĻ
    0.06
    eee
    0.06
    kat
    0.06
    ifestyles
    0.06
    AMES
    0.06
    emento
    0.06
    sbin
    0.06
    è¼
    0.06
    Activations Density 0.029%

    No Known Activations