© 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. 60716
    Prev
    Next
    INDEX
    Explanations

    first-person and second-person personal pronouns and references to family dynamics

    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
    outine
    -0.08
    APT
    -0.07
    GuidId
    -0.07
    rlen
    -0.07
    azine
    -0.07
    edik
    -0.07
    idores
    -0.07
    ault
    -0.07
    ginas
    -0.07
    agnost
    -0.06
    POSITIVE LOGITS
    antal
    0.07
    513
    0.06
    ãĤ¿ãĥ¼
    0.06
    'll
    0.06
    877
    0.06
     should
    0.06
    IEL
    0.06
     going
    0.06
    ’ll
    0.06
    mini
    0.06
    Activations Density 0.054%

    No Known Activations