© 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. 89044
    Prev
    Next
    INDEX
    Explanations

    instances of the word "below" and similar variations referring to depth or lower levels

    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
    uyá»ĩt
    -0.07
    lite
    -0.06
    way
    -0.06
    以æĿ¥
    -0.06
     پرد
    -0.06
    /place
    -0.06
    /load
    -0.06
    à¥įà¤
    -0.06
    cken
    -0.06
    amen
    -0.06
    POSITIVE LOGITS
    neath
    0.11
    -average
    0.08
    .gdx
    0.08
    icz
    0.08
    /out
    0.07
    razier
    0.07
    jÅ¡ÃŃ
    0.07
    oup
    0.07
    /up
    0.07
    -zero
    0.07
    Activations Density 0.017%

    No Known Activations