© 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 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. 129038
    Prev
    Next
    INDEX
    Explanations

    references to books and their authors

    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
    å¸Ń
    -0.07
     pieces
    -0.06
    naires
    -0.06
    ongs
    -0.06
    /stretch
    -0.06
    úc
    -0.06
    éĽĦ
    -0.05
    anges
    -0.05
    alty
    -0.05
    umont
    -0.05
    POSITIVE LOGITS
    review
    0.11
    -review
    0.10
     review
    0.10
    ariant
    0.08
     Review
    0.08
    _review
    0.08
     reviewer
    0.07
    Review
    0.07
    arent
    0.07
    uard
    0.07
    Activations Density 0.020%

    No Known Activations