© 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. 116776
    Prev
    Next
    INDEX
    Explanations

    instances of access permissions in code

    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
    iversit
    -0.07
    amina
    -0.06
    ocu
    -0.06
    244
    -0.06
    amen
    -0.06
    wright
    -0.06
    tright
    -0.06
    preneur
    -0.06
    oog
    -0.06
    иÑĤив
    -0.06
    POSITIVE LOGITS
     Ñģпад
    0.06
    athy
    0.06
    imir
    0.06
    isode
    0.06
    tails
    0.06
    als
    0.06
    asan
    0.06
    tion
    0.06
    æºĢ
    0.06
     Gui
    0.06
    Activations Density 0.000%

    No Known Activations