© 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. 118905
    Prev
    Next
    INDEX
    Explanations

    phrases and words that indicate instances of economic decline or distress

    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
    inke
    -0.07
    BOT
    -0.07
    alsex
    -0.07
    olleyError
    -0.07
    ót
    -0.06
    ypad
    -0.06
    nicos
    -0.06
    æī¬
    -0.06
    акон
    -0.06
    (Material
    -0.06
    POSITIVE LOGITS
     chez
    0.07
     testimon
    0.06
     Diagnostic
    0.06
     Ab
    0.06
     some
    0.06
     ab
    0.06
     resident
    0.06
    æ²»
    0.06
     sitting
    0.06
     young
    0.05
    Activations Density 0.040%

    No Known Activations