© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71841
    Prev
    Next
    INDEX
    Explanations

    possessive and relational terms related to individuals and their connections

    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
    ãĥ«ãĥĪ
    -0.08
    _Tis
    -0.08
    URRED
    -0.08
    $MESS
    -0.07
    çĩ
    -0.07
    EMPLARY
    -0.07
    éīĦ
    -0.07
    å¼ĭ
    -0.07
    ãĥĭãĥ¼
    -0.07
    ombok
    -0.07
    POSITIVE LOGITS
     Cardinals
    0.09
     Vatican
    0.08
     card
    0.07
     Marty
    0.07
     Clement
    0.07
     Rome
    0.07
     Cardinal
    0.07
     pap
    0.07
     Innoc
    0.06
     St
    0.06
    Activations Density 0.002%

    No Known Activations