© 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. 120915
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Ben"

    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
    erot
    -0.08
    ahat
    -0.08
    uctor
    -0.07
    osci
    -0.07
    vette
    -0.07
    villa
    -0.06
    phant
    -0.06
    genic
    -0.06
    onaut
    -0.06
    argon
    -0.06
    POSITIVE LOGITS
    jamin
    0.09
    ninger
    0.09
    ekli
    0.08
    oit
    0.08
    ning
    0.07
    جاÙħ
    0.07
    oir
    0.07
    ÃŃte
    0.07
    ign
    0.07
    ito
    0.07
    Activations Density 0.009%

    No Known Activations