© 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. 54770
    Prev
    Next
    INDEX
    Explanations

    references to familial or organizational relationships

    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
    ogen
    -0.06
     Buch
    -0.06
    tor
    -0.06
    /to
    -0.05
     Bound
    -0.05
    اپ
    -0.05
    oph
    -0.05
     those
    -0.05
     Aid
    -0.05
     æ®
    -0.05
    POSITIVE LOGITS
    edBy
    0.08
    ÑĢÑıдÑĥ
    0.08
     sister
    0.07
    Qualifier
    0.07
    ething
    0.07
    iddleware
    0.07
    remainder
    0.07
    Sibling
    0.07
    lenen
    0.07
    IPH
    0.07
    Activations Density 0.008%

    No Known Activations