© 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. 62810
    Prev
    Next
    INDEX
    Explanations

    repeated usage of the word "the" and references to locations or objects in a narrative context

    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
    jur
    -0.07
    auss
    -0.06
    .paths
    -0.06
    ãĥ¼ãĥĬ
    -0.06
     sorts
    -0.06
    avar
    -0.06
    å¨ĺ
    -0.06
    iye
    -0.06
    a
    -0.06
    iller
    -0.06
    POSITIVE LOGITS
     PARTICULAR
    0.07
    arine
    0.07
    roduce
    0.06
    @nate
    0.06
     center
    0.06
     Donovan
    0.06
    ÑĢовиÑĩ
    0.06
    ocale
    0.06
    ersen
    0.06
     emb
    0.06
    Activations Density 0.041%

    No Known Activations