© 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. 94691
    Prev
    Next
    INDEX
    Explanations

    references to familial or interpersonal relationships in narrative contexts

    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
    มà¸Ļ
    -0.08
    gs
    -0.07
    .ua
    -0.07
    èªł
    -0.07
    adier
    -0.06
     Bilg
    -0.06
    ÄįnÃŃk
    -0.06
    elman
    -0.06
    isos
    -0.06
    GS
    -0.06
    POSITIVE LOGITS
    uche
    0.08
    058
    0.07
    asha
    0.06
    551
    0.06
    iko
    0.06
     Weaver
    0.06
    ough
    0.06
     Cob
    0.06
     بÙĦÙĨد
    0.06
    ought
    0.06
    Activations Density 0.096%

    No Known Activations