© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 62526
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and related references to individuals or groups

    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
    aki
    -0.07
    ÑģÑĤиÑĩ
    -0.07
    oÅĽci
    -0.06
    çĵ
    -0.06
    ision
    -0.06
    erap
    -0.06
    ucid
    -0.06
    velopment
    -0.06
    heim
    -0.06
    ög
    -0.06
    POSITIVE LOGITS
    fdc
    0.07
    ledo
    0.07
    HAM
    0.06
    llx
    0.06
     Mills
    0.06
     kred
    0.06
    dic
    0.06
    scatter
    0.06
    çĮ
    0.06
     extent
    0.06
    Activations Density 0.009%

    No Known Activations