© 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. 71990
    Prev
    Next
    INDEX
    Explanations

    references to music reviews and critiques

    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
    üz
    -0.07
     away
    -0.06
    appy
    -0.06
    uz
    -0.06
    aira
    -0.06
    dra
    -0.06
    hma
    -0.05
    exampleInput
    -0.05
    tele
    -0.05
    zial
    -0.05
    POSITIVE LOGITS
     reviewer
    0.13
     review
    0.11
    -review
    0.10
     reviewers
    0.10
     reviews
    0.10
     reviewing
    0.10
    review
    0.10
    Reviewer
    0.10
    reviews
    0.10
    Reviews
    0.09
    Activations Density 0.023%

    No Known Activations