© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 106604
    Prev
    Next
    INDEX
    Explanations

    personal pronouns indicating first-person perspective

    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
    omez
    -0.08
    eme
    -0.07
    ån
    -0.07
    ëįķ
    -0.07
     bestimm
    -0.07
    regor
    -0.07
    olini
    -0.07
     expectedResult
    -0.07
    legate
    -0.07
    oly
    -0.07
    POSITIVE LOGITS
     countered
    0.08
     counter
    0.07
     instead
    0.07
     disagrees
    0.07
     retal
    0.07
     naopak
    0.07
     Decompiled
    0.07
     however
    0.06
     overhe
    0.06
    åıį
    0.06
    Activations Density 0.029%

    No Known Activations