© 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. 76697
    Prev
    Next
    INDEX
    Explanations

    phrases related to fleeing or escaping from a situation

    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
     dÄ±ÅŁÄ±
    -0.07
    екÑĤÑĥ
    -0.06
    889
    -0.06
    888
    -0.06
    abus
    -0.06
     TOUR
    -0.06
    alles
    -0.06
    917
    -0.06
    _fatal
    -0.06
    808
    -0.06
    POSITIVE LOGITS
     fled
    0.07
    sko
    0.06
    opa
    0.06
    ovah
    0.06
    aad
    0.06
    YD
    0.06
    letes
    0.06
    yd
    0.06
    kla
    0.06
    .bi
    0.06
    Activations Density 0.006%

    No Known Activations