© 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. 30639
    Prev
    Next
    INDEX
    Explanations

    words related to funding, grants, and support in various projects and studies

    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
    uisse
    -0.08
    lech
    -0.07
    _ASSUME
    -0.07
    ple
    -0.07
    okt
    -0.07
    ãĥķãĥĪ
    -0.07
    ibri
    -0.07
     nÃło
    -0.07
    frei
    -0.07
    _POINTER
    -0.07
    POSITIVE LOGITS
    erring
    0.06
    iker
    0.06
    rame
    0.06
     itself
    0.06
     rencont
    0.06
    azi
    0.06
     which
    0.06
    NSNotification
    0.06
    ramework
    0.05
    XHR
    0.05
    Activations Density 0.039%

    No Known Activations