© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 87323
    Prev
    Next
    INDEX
    Explanations

    instances of the word "escape" and its variations, particularly related to physical or metaphorical freedom

    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
    ãģĹãĤĩ
    -0.07
    igest
    -0.07
    urtle
    -0.06
    lements
    -0.06
    -extension
    -0.06
    ToolStrip
    -0.06
    ringe
    -0.06
    achi
    -0.06
    uts
    -0.06
    inan
    -0.06
    POSITIVE LOGITS
    olini
    0.07
     khá»ıi
    0.07
    elman
    0.07
    elyn
    0.06
    esini
    0.06
    ble
    0.06
    lyn
    0.06
    uele
    0.06
    heet
    0.06
     glyphicon
    0.06
    Activations Density 0.005%

    No Known Activations