© 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. 87765
    Prev
    Next
    INDEX
    Explanations

    first-person personal pronouns and statements of ownership or experience

    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
     Olson
    -0.06
    etical
    -0.06
    ifecycle
    -0.06
    Æ°Æ¡ng
    -0.06
    immel
    -0.06
    folk
    -0.06
     strav
    -0.06
    xde
    -0.06
    ãĥ³ãĤ¯
    -0.06
     versions
    -0.06
    POSITIVE LOGITS
     recently
    0.09
     recent
    0.08
     someone
    0.07
    recent
    0.07
     called
    0.07
    enga
    0.07
    elsey
    0.07
     somebody
    0.07
    ero
    0.06
     hadn
    0.06
    Activations Density 0.025%

    No Known Activations