© 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. 81076
    Prev
    Next
    INDEX
    Explanations

    elements related to significant thematic details in stories or narratives

    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
     jadx
    -0.07
    chnitt
    -0.07
    夫
    -0.07
    asket
    -0.07
    urator
    -0.07
    Toast
    -0.07
     Grinder
    -0.07
    ulla
    -0.07
     Dud
    -0.06
    unker
    -0.06
    POSITIVE LOGITS
     children
    0.15
     Children
    0.13
     kids
    0.12
    Children
    0.12
    children
    0.11
     child
    0.11
     Childhood
    0.11
     childhood
    0.11
     CHILD
    0.10
     kid
    0.10
    Activations Density 0.002%

    No Known Activations