© 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. 92277
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns indicating ownership or association

    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
    681
    -0.07
    eren
    -0.07
    égor
    -0.07
    adiens
    -0.07
    rug
    -0.06
    ancode
    -0.06
     proport
    -0.06
    etine
    -0.06
    andles
    -0.06
    .export
    -0.06
    POSITIVE LOGITS
    çł
    0.06
    elt
    0.06
    .newBuilder
    0.06
     pr
    0.06
    advance
    0.06
    .TEXTURE
    0.06
    ween
    0.06
     _
    0.06
     fel
    0.06
    tolist
    0.05
    Activations Density 0.049%

    No Known Activations