© 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. 85717
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or instructions that involve repetition or listing

    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
    avit
    -0.09
    iaux
    -0.07
     simply
    -0.07
    appa
    -0.07
     merely
    -0.07
    only
    -0.07
    atre
    -0.06
    arih
    -0.06
    adir
    -0.06
    createClass
    -0.06
    POSITIVE LOGITS
    chor
    0.06
    assel
    0.06
    @test
    0.06
    ymb
    0.06
    sy
    0.06
    uyla
    0.06
     hazard
    0.06
    -num
    0.06
     Marshal
    0.05
    iero
    0.05
    Activations Density 0.007%

    No Known Activations