© 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. 70426
    Prev
    Next
    INDEX
    Explanations

    questions about frequency and quantity

    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
     may
    -0.07
    ierge
    -0.07
     and
    -0.07
    our
    -0.06
    '
    -0.06
    äºĭæĥħ
    -0.06
    ;
    -0.06
    or
    -0.06
     pun
    -0.06
     inclusive
    -0.06
    POSITIVE LOGITS
    ÄĻż
    0.09
    uetype
    0.07
    ofday
    0.07
    Uvs
    0.07
    .ToolStrip
    0.07
    Truthy
    0.07
    ÏĢλ
    0.07
    etooth
    0.07
     yourself
    0.07
    çİ
    0.07
    Activations Density 0.014%

    No Known Activations