© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 89677
    Prev
    Next
    INDEX
    Explanations

    first-person and third-person pronouns

    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
    PÅĻed
    -0.07
     ìı
    -0.07
    amba
    -0.06
    posables
    -0.06
     aras
    -0.06
    ãĤĵãģ©
    -0.06
    ocu
    -0.06
    ëįĺ
    -0.06
     Mojo
    -0.06
    ucc
    -0.06
    POSITIVE LOGITS
     certainly
    0.13
     definitely
    0.08
    UA
    0.08
     Certainly
    0.07
     plenty
    0.07
    isma
    0.06
    ä¹Łä¸į
    0.06
     sÃŃ
    0.06
     also
    0.06
    sert
    0.06
    Activations Density 0.026%

    No Known Activations