© 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. 107977
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and related web resources

    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
    gnu
    -0.07
    hle
    -0.07
    _FRAMEBUFFER
    -0.06
    ساÙĦ
    -0.06
    idable
    -0.06
    _$_
    -0.06
    ovah
    -0.06
    linky
    -0.06
    ìĬ¤íĥĢ
    -0.06
    αÏģά
    -0.06
    POSITIVE LOGITS
    alance
    0.07
    /search
    0.07
     Keyword
    0.07
    (search
    0.06
    ues
    0.06
    atra
    0.06
     search
    0.06
    arrant
    0.06
    .search
    0.06
     Search
    0.06
    Activations Density 0.018%

    No Known Activations