© 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 EvalsExportsAPI 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. 105880
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Dar" and related variations or forms

    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
    är
    -0.08
    erson
    -0.07
    essen
    -0.07
    orpion
    -0.07
    ited
    -0.07
    erty
    -0.07
    irt
    -0.07
    ihat
    -0.07
    iard
    -0.07
    اÙģÙĬØ©
    -0.06
    POSITIVE LOGITS
    nton
    0.08
    devil
    0.07
    lene
    0.07
    leigh
    0.07
     otherwise
    0.07
    lington
    0.07
    ÃŃo
    0.07
    ziel
    0.06
    croll
    0.06
    adia
    0.06
    Activations Density 0.009%

    No Known Activations