© 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. 78878
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "in."

    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
    chte
    -0.06
    .Enums
    -0.06
    ádu
    -0.06
    áv
    -0.06
     beh
    -0.06
     Kauf
    -0.06
    plr
    -0.06
     excess
    -0.06
    ipop
    -0.05
     dress
    -0.05
    POSITIVE LOGITS
     general
    0.11
    general
    0.10
     général
    0.09
     geral
    0.09
     generally
    0.09
    _general
    0.08
    -general
    0.08
     عاÙħØ©
    0.08
     вообÑīе
    0.08
     itself
    0.08
    Activations Density 0.051%

    No Known Activations