© 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 EvalsExportsinterp-engineNEWAPI 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. 69766
    Prev
    Next
    INDEX
    Explanations

    words related to grammatical categories, specifically adjectives and pronouns

    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
    heim
    -0.07
    raci
    -0.07
    .CodeAnalysis
    -0.07
    ustin
    -0.07
     gấp
    -0.06
    åij
    -0.06
    SYS
    -0.06
    info
    -0.06
    514
    -0.06
    anio
    -0.06
    POSITIVE LOGITS
    éĴ®
    0.07
    наÑĢ
    0.07
    urtles
    0.06
     Bord
    0.06
    åı·
    0.06
    Ñıд
    0.06
    .sg
    0.06
    ặng
    0.06
    memberof
    0.06
    idelberg
    0.06
    Activations Density 0.012%

    No Known Activations