© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 124909
    Prev
    Next
    INDEX
    Explanations

    names and references to characters or prominent individuals in a narrative context

    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
    ahan
    -0.07
    652
    -0.07
    ann
    -0.07
    cox
    -0.07
    ahl
    -0.07
    ãĤ«ãĥ¼
    -0.06
    dea
    -0.06
    uk
    -0.06
    wyn
    -0.06
    058
    -0.06
    POSITIVE LOGITS
     del
    0.08
     de
    0.08
    еÑĢо
    0.07
    idue
    0.07
    itos
    0.07
    idel
    0.07
    epam
    0.07
     Osc
    0.06
     Labrador
    0.06
    IENT
    0.06
    Activations Density 0.168%

    No Known Activations