© 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. 55175
    Prev
    Next
    INDEX
    Explanations

    punctuation and sentence structure

    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
    ichtig
    -0.07
    ihat
    -0.07
    à¹ĭ
    -0.06
    çĥ¦
    -0.06
    >{!!
    -0.06
    oss
    -0.06
    alaxy
    -0.06
    anium
    -0.06
    ughter
    -0.06
    éģĩ
    -0.06
    POSITIVE LOGITS
    chodu
    0.07
    imers
    0.06
     Lod
    0.06
    LBL
    0.06
    onen
    0.06
     <!--[
    0.06
     tempor
    0.06
    intr
    0.06
     advice
    0.06
    rof
    0.06
    Activations Density 0.036%

    No Known Activations