© 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. 119656
    Prev
    Next
    INDEX
    Explanations

    specific numerical data, particularly related to yearly statistics or identifiers

    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
    ÅĻi
    -0.07
     lately
    -0.07
    ennis
    -0.07
    öyle
    -0.07
    éĨ´
    -0.07
    OWL
    -0.07
    γγελ
    -0.06
    WARDED
    -0.06
    ÑĤоÑĢа
    -0.06
    ç«ĭãģ¦
    -0.06
    POSITIVE LOGITS
     edition
    0.09
    edition
    0.08
    /.
    0.07
     Edition
    0.07
     iteration
    0.07
    trs
    0.06
    phinx
    0.06
     version
    0.06
    ails
    0.06
    /'
    0.06
    Activations Density 0.017%

    No Known Activations