© 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. 42123
    Prev
    Next
    INDEX
    Explanations

    narratives involving personal connections and family 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
     Walton
    -0.06
    Bindings
    -0.06
    ç¾½
    -0.06
    asions
    -0.06
    039
    -0.06
    ynth
    -0.06
    xffffff
    -0.06
     è±
    -0.06
    uner
    -0.06
    ondon
    -0.06
    POSITIVE LOGITS
     heard
    0.13
    heard
    0.12
     saw
    0.10
     seen
    0.09
    seen
    0.09
     Heard
    0.09
     recently
    0.09
     reports
    0.08
     recent
    0.08
     noticed
    0.08
    Activations Density 0.069%

    No Known Activations