© 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. 85074
    Prev
    Next
    INDEX
    Explanations

    names and references to notable individuals involved in controversies or scandals

    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
    otton
    -0.09
    erti
    -0.08
    ATUS
    -0.08
    biên
    -0.07
    Äįku
    -0.07
    infeld
    -0.07
    à¸Ĺาà¸ĩà¸ģาร
    -0.07
    ancode
    -0.07
    sale
    -0.07
    loe
    -0.07
    POSITIVE LOGITS
    igans
    0.06
     Barrett
    0.06
     Goodman
    0.06
    orption
    0.05
     FI
    0.05
     sc
    0.05
    375
    0.05
     experimental
    0.05
    anch
    0.05
     Sab
    0.05
    Activations Density 0.000%

    No Known Activations