© 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. 79980
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in" and related spatial or positional phrases

    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
    izz
    -0.06
     meis
    -0.06
    dens
    -0.06
    VERR
    -0.06
    -bordered
    -0.06
    667
    -0.06
    afa
    -0.06
    vio
    -0.06
    atis
    -0.06
    enes
    -0.06
    POSITIVE LOGITS
    lay
    0.09
    uo
    0.07
     position
    0.07
     lay
    0.07
    esta
    0.07
    umber
    0.07
    estic
    0.06
    kaar
    0.06
     positions
    0.06
    LAY
    0.06
    Activations Density 0.043%

    No Known Activations