© 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. 61299
    Prev
    Next
    INDEX
    Explanations

    words associated with realism in various contexts

    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
    arov
    -0.07
    yards
    -0.07
    esis
    -0.07
     rés
    -0.07
     rencontres
    -0.07
    forth
    -0.07
    aren
    -0.07
     Rencontres
    -0.07
    ela
    -0.07
    laws
    -0.07
    POSITIVE LOGITS
    istically
    0.13
    igned
    0.12
    istic
    0.10
    ignment
    0.10
    -life
    0.10
    ationship
    0.09
    -world
    0.09
     estate
    0.09
    izable
    0.08
    iable
    0.08
    Activations Density 0.054%

    No Known Activations