© 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. 61364
    Prev
    Next
    INDEX
    Explanations

    references to heraldry and symbols associated with magistrates

    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
    ioni
    -0.08
    lore
    -0.07
    rov
    -0.07
    ære
    -0.07
    omin
    -0.07
     Hizmetleri
    -0.07
    .XR
    -0.07
     suce
    -0.07
    kiem
    -0.07
    rame
    -0.07
    POSITIVE LOGITS
    人çī©
    0.07
    eh
    0.06
     household
    0.06
    çīĻ
    0.06
     Horm
    0.06
    Ups
    0.06
     Hubbard
    0.06
     seems
    0.06
     ban
    0.06
     seem
    0.06
    Activations Density 0.010%

    No Known Activations