© 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. 71333
    Prev
    Next
    INDEX
    Explanations

    poetic imagery and descriptive language

    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
    stro
    -0.07
    lse
    -0.06
    oin
    -0.06
    azz
    -0.06
    802
    -0.05
    aign
    -0.05
     Gerr
    -0.05
    scape
    -0.05
    .builders
    -0.05
    rech
    -0.05
    POSITIVE LOGITS
    ़à¤ķ
    0.07
    hek
    0.06
    .Attach
    0.06
    euillez
    0.06
    ypad
    0.06
    .cloudflare
    0.06
    isy
    0.06
    лиÑĪком
    0.06
    ude
    0.06
    ãĥ¬ãĥ¼
    0.06
    Activations Density 0.003%

    No Known Activations