© 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. 30853
    Prev
    Next
    INDEX
    Explanations

    HTML or PHP tag structures in the text

    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
    reur
    -0.06
    rippling
    -0.06
    Inset
    -0.06
    ordion
    -0.06
    Outlined
    -0.06
     allowable
    -0.05
    ushima
    -0.05
    rir
    -0.05
    ANDOM
    -0.05
    ringe
    -0.05
    POSITIVE LOGITS
    jem
    0.07
    antan
    0.07
    гов
    0.06
    zdy
    0.06
    quina
    0.06
     fou
    0.06
    entai
    0.06
    _EOF
    0.06
    æĪ·
    0.06
    vů
    0.06
    Activations Density 0.022%

    No Known Activations