© 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. 60568
    Prev
    Next
    INDEX
    Explanations

    names of characters or actors in films

    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
    Ìģ
    -0.08
     (
    -0.08
    456
    -0.07
     credentials
    -0.07
    apel
    -0.07
     discomfort
    -0.06
     Weinstein
    -0.06
    ivot
    -0.06
     Credentials
    -0.06
    achten
    -0.06
    POSITIVE LOGITS
    TOTYPE
    0.08
    avaÅŁ
    0.07
    sales
    0.07
    ìļĶ
    0.07
    ropp
    0.07
     vraiment
    0.07
     addCriterion
    0.07
     quake
    0.06
    .sales
    0.06
    ãģķãģ¾
    0.06
    Activations Density 0.000%

    No Known Activations