© 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. 9-LLAMASCOPE-RES-131K
    11. 97768
    Prev
    Next
    INDEX
    Explanations

    structured programming elements and references

    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
    æľ
    -0.07
    اختÛĮ
    -0.07
    dam
    -0.07
    оÑĢд
    -0.06
    enha
    -0.06
    uti
    -0.06
    REATED
    -0.06
    yk
    -0.06
    shield
    -0.06
    _SHIFT
    -0.06
    POSITIVE LOGITS
    Ïĥμα
    0.06
     Bye
    0.06
    oppel
    0.06
    òng
    0.06
     Manning
    0.06
    azen
    0.06
    èĢ
    0.06
    habi
    0.06
    mouseout
    0.06
    opi
    0.06
    Activations Density 0.208%

    No Known Activations