© 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. 15521
    Prev
    Next
    INDEX
    Explanations

    sentences that include inquiries or statements about personal information and 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
    ylie
    -0.07
    mani
    -0.07
    ãĥĥãĥĪ
    -0.06
    ická
    -0.06
    dao
    -0.06
    çĪ½
    -0.06
    веÑī
    -0.06
    ħ
    -0.06
    LIKELY
    -0.06
     kot
    -0.06
    POSITIVE LOGITS
     Bes
    0.07
    anki
    0.07
    Bes
    0.07
    653
    0.06
     Bay
    0.06
    Ø´ÙħارÛĮ
    0.06
    elo
    0.06
    çĶ
    0.06
    ãĥĸ
    0.06
    ible
    0.06
    Activations Density 0.010%

    No Known Activations