© 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. 93241
    Prev
    Next
    INDEX
    Explanations

    instances of the word "encounter" or its variations, indicating a focus on experiences and interactions

    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
    ãģĦãĤĭ
    -0.08
    undler
    -0.08
    ÙĪÙĨا
    -0.08
    Äįka
    -0.08
    enge
    -0.08
    ÑģоÑĤ
    -0.07
    aturas
    -0.07
    igger
    -0.07
    ullets
    -0.07
    ighth
    -0.07
    POSITIVE LOGITS
    ments
    0.08
    icut
    0.08
    odings
    0.07
    ables
    0.07
    inges
    0.07
    inge
    0.07
    InThe
    0.07
    ives
    0.07
    ances
    0.07
    /ex
    0.07
    Activations Density 0.007%

    No Known Activations