© 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. 26945
    Prev
    Next
    INDEX
    Explanations

    phrases that convey emotional or human connections

    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
     bore
    -0.07
    ew
    -0.06
    lech
    -0.06
    en
    -0.06
    ij
    -0.06
    etus
    -0.06
    yn
    -0.06
    chest
    -0.06
     Christie
    -0.06
    cket
    -0.06
    POSITIVE LOGITS
    alth
    0.07
    phylum
    0.07
    fork
    0.07
    ÑĢÑĸд
    0.06
    :str
    0.06
     Ä°st
    0.06
     thiên
    0.06
    ecut
    0.06
    ženÃŃ
    0.06
     nÃŃ
    0.06
    Activations Density 0.006%

    No Known Activations