© 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 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. 17-LLAMASCOPE-RES-131K
    11. 85597
    Prev
    Next
    INDEX
    Explanations

    possessive forms indicating familial 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
    lah
    -0.07
    ä¸ĢåĪĩ
    -0.07
     Families
    -0.07
    dad
    -0.07
     LENG
    -0.06
    itarian
    -0.06
     BÃł
    -0.06
    ï¸
    -0.06
    #{@
    -0.06
    åıĬåħ¶
    -0.06
    POSITIVE LOGITS
     legacy
    0.07
    otti
    0.06
     similarly
    0.06
    legacy
    0.06
    ObjectContext
    0.06
    _phy
    0.06
    Ñģион
    0.06
    quire
    0.06
    enco
    0.06
    praak
    0.06
    Activations Density 0.013%

    No Known Activations