© 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. 54406
    Prev
    Next
    INDEX
    Explanations

    references to professional roles and contributions in various fields

    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
    иÑģлов
    -0.08
    atica
    -0.08
    AREST
    -0.07
    ouri
    -0.07
    attern
    -0.07
    ãĥ«ãĤ¯
    -0.07
    ombine
    -0.07
    ouro
    -0.07
    amet
    -0.07
    ilos
    -0.07
    POSITIVE LOGITS
     on
    0.08
     at
    0.07
     elsewhere
    0.06
     in
    0.06
    ahu
    0.06
    lain
    0.06
    Ñħ
    0.06
    inz
    0.06
     loyal
    0.06
    Ĭ¶
    0.06
    Activations Density 0.020%

    No Known Activations