© 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. 93829
    Prev
    Next
    INDEX
    Explanations

    instances of the word "this."

    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
    ov
    -0.06
    ional
    -0.06
    end
    -0.06
    idor
    -0.06
    pt
    -0.06
    .Localization
    -0.06
    E
    -0.06
    ÅĽci
    -0.06
    yt
    -0.05
    af
    -0.05
    POSITIVE LOGITS
    ntax
    0.09
    gba
    0.07
    ylon
    0.07
    GMEM
    0.07
    ichi
    0.07
    licas
    0.07
    activex
    0.07
    earer
    0.07
    azu
    0.07
    rzy
    0.07
    Activations Density 0.042%

    No Known Activations