© 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. 82362
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of places, organizations, and characters

    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
    undos
    -0.07
    μÏĢο
    -0.07
    маз
    -0.07
    ONTAL
    -0.07
    toi
    -0.07
    _Long
    -0.07
    ãĤĵãģ©
    -0.07
    заб
    -0.06
    ãģģ
    -0.06
    aths
    -0.06
    POSITIVE LOGITS
    radient
    0.06
    dddd
    0.06
    orney
    0.06
     Rahman
    0.06
    iegel
    0.06
    dic
    0.06
    elo
    0.06
     Pradesh
    0.06
    dad
    0.06
     Fucking
    0.06
    Activations Density 0.079%

    No Known Activations