© 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. 56821
    Prev
    Next
    INDEX
    Explanations

    nouns and concepts associated with specific places, events, and products

    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
    fur
    -0.07
    olley
    -0.06
     repr
    -0.06
    or
    -0.06
    anka
    -0.05
     Sanct
    -0.05
     mol
    -0.05
    eden
    -0.05
    exo
    -0.05
    ILINE
    -0.05
    POSITIVE LOGITS
    -wide
    0.13
    wide
    0.11
    -specific
    0.09
     wide
    0.08
    _specific
    0.08
    pecific
    0.08
    Wide
    0.08
     Wide
    0.08
     nét
    0.08
    ТÐŀ
    0.08
    Activations Density 0.082%

    No Known Activations