© 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. 118685
    Prev
    Next
    INDEX
    Explanations

    references to narrative elements and concepts associated with storytelling or sequences of events

    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
    è¾°
    -0.08
     Victim
    -0.06
    htub
    -0.06
     tra
    -0.06
    ichi
    -0.06
    victim
    -0.06
    elow
    -0.06
    reed
    -0.06
    sher
    -0.06
    лев
    -0.06
    POSITIVE LOGITS
    uron
    0.08
    oggler
    0.07
    oggle
    0.07
    imeline
    0.07
    rial
    0.06
    kees
    0.06
     FAST
    0.06
    ulla
    0.06
     rast
    0.06
     QName
    0.06
    Activations Density 0.000%

    No Known Activations