© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 86705
    Prev
    Next
    INDEX
    Explanations

    certain punctuation marks in the document

    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
    s
    -0.11
    i
    -0.09
    in
    -0.08
    t
    -0.08
    nt
    -0.08
    z
    -0.07
    es
    -0.07
    e
    -0.07
    alytics
    -0.07
    tti
    -0.07
    POSITIVE LOGITS
    @nate
    0.08
    ï¸ı
    0.08
    ‘
    0.07
    .ImageAlign
    0.07
    ogle
    0.07
    gle
    0.07
    etc
    0.06
    ìħľ
    0.06
    AVA
    0.06
    \/
    0.06
    Activations Density 0.118%

    No Known Activations