© 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. 2597
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific names

    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
    verse
    -0.07
    rik
    -0.07
    arity
    -0.07
    usive
    -0.06
    ways
    -0.06
    trs
    -0.06
    beam
    -0.06
    isé
    -0.06
    ting
    -0.06
    phies
    -0.06
    POSITIVE LOGITS
    emie
    0.08
    ethoven
    0.07
    ramework
    0.07
    iful
    0.07
    otime
    0.07
    emy
    0.07
    405
    0.07
    avier
    0.07
     latter
    0.07
    otted
    0.07
    Activations Density 0.027%

    No Known Activations