© 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. 62092
    Prev
    Next
    INDEX
    Explanations

    pronouns and reflexive 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
    apl
    -0.07
    ÑģÑı
    -0.06
    .attribute
    -0.06
    ábado
    -0.06
    kem
    -0.06
    antor
    -0.06
    (æ°´
    -0.06
    tos
    -0.06
    ucid
    -0.06
    ghan
    -0.06
    POSITIVE LOGITS
    usk
    0.07
    865
    0.07
     sebagai
    0.07
     Og
    0.07
    arken
    0.06
    /us
    0.06
    imbus
    0.06
    yr
    0.06
     ActionTypes
    0.06
     differently
    0.06
    Activations Density 0.017%

    No Known Activations