© 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. 9-LLAMASCOPE-RES-131K
    11. 95125
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly quotation marks

    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
    iveness
    -0.06
    ej
    -0.06
    un
    -0.06
    udi
    -0.05
    163
    -0.05
    edin
    -0.05
    553
    -0.05
     Cock
    -0.05
     conserv
    -0.05
     Hel
    -0.05
    POSITIVE LOGITS
     Karlov
    0.08
     acomp
    0.07
    loha
    0.07
     INCIDENT
    0.07
    _singleton
    0.07
    رÙĬØ·
    0.07
    ãĥ«ãĥķ
    0.07
    ipt
    0.07
    recio
    0.07
    jev
    0.07
    Activations Density 0.000%

    No Known Activations