© 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. 58445
    Prev
    Next
    INDEX
    Explanations

    conjunctions, particularly the word "and" in various contexts

    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
    idal
    -0.09
    erais
    -0.07
    unner
    -0.07
    éľ
    -0.07
    ibu
    -0.06
     Bren
    -0.06
    swire
    -0.06
    orsk
    -0.06
    erva
    -0.06
    rief
    -0.06
    POSITIVE LOGITS
     sometimes
    0.07
     bazen
    0.06
    amenti
    0.06
    249
    0.06
     perhaps
    0.06
     possibly
    0.06
    avax
    0.06
    asters
    0.05
    èŃ°
    0.05
    andbox
    0.05
    Activations Density 0.016%

    No Known Activations