© 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. 93030
    Prev
    Next
    INDEX
    Explanations

    information related to educational institutions and their attributes

    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
    our
    -0.07
    aret
    -0.07
    ó
    -0.06
    oca
    -0.06
    oure
    -0.06
    ama
    -0.06
    let
    -0.06
    .cbo
    -0.06
    -facing
    -0.06
    atha
    -0.06
    POSITIVE LOGITS
     â
    0.08
    iversit
    0.07
    reira
    0.07
    stance
    0.07
    ernel
    0.07
    ovny
    0.07
    lisi
    0.06
    ovna
    0.06
    (çģ«
    0.06
    'aff
    0.06
    Activations Density 0.002%

    No Known Activations