© 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. 75464
    Prev
    Next
    INDEX
    Explanations

    themes related to conflict and emotional experiences in stories

    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
    orWhere
    -0.09
    oling
    -0.07
    yen
    -0.07
    ichel
    -0.07
    знаÑĩа
    -0.07
    Ñģен
    -0.07
    ouden
    -0.07
    SizeMode
    -0.07
    igte
    -0.07
    -addon
    -0.07
    POSITIVE LOGITS
     families
    0.07
     roles
    0.07
     war
    0.07
     experience
    0.07
     Quarter
    0.06
     civilians
    0.06
     War
    0.06
     documentation
    0.06
     participation
    0.06
     ordinary
    0.06
    Activations Density 0.020%

    No Known Activations