© 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. 118693
    Prev
    Next
    INDEX
    Explanations

    narrative elements related to escape or fleeing

    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
     çģ
    -0.06
    heiro
    -0.06
    uctive
    -0.06
    uben
    -0.06
    lli
    -0.06
    ega
    -0.06
    ious
    -0.05
    лл
    -0.05
     int
    -0.05
    åĭĻ
    -0.05
    POSITIVE LOGITS
    addtogroup
    0.08
    деÑĢ
    0.08
    Äĵ
    0.07
    essian
    0.07
    Gün
    0.07
    ibi
    0.07
    .libs
    0.07
    Neutral
    0.07
    ctl
    0.07
    placeholders
    0.07
    Activations Density 0.006%

    No Known Activations