© 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. 27408
    Prev
    Next
    INDEX
    Explanations

    elements related to written work and academic writing 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
    .yy
    -0.07
    geries
    -0.07
    adol
    -0.07
    lied
    -0.07
     yat
    -0.07
    ãĥ³ãĥĸ
    -0.07
    dac
    -0.07
     nues
    -0.07
     Phonetic
    -0.07
    ifestyles
    -0.06
    POSITIVE LOGITS
     youre
    0.07
     Pap
    0.07
     chapter
    0.06
     Sty
    0.06
     GRE
    0.06
    your
    0.06
    folio
    0.06
     research
    0.06
    GRE
    0.06
    Usually
    0.06
    Activations Density 0.016%

    No Known Activations