© 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. 87583
    Prev
    Next
    INDEX
    Explanations

    specific scene references and structural elements in narrative content

    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
    éĵ¶
    -0.07
    orners
    -0.07
    å±Ĭ
    -0.06
    Äįen
    -0.06
    ephy
    -0.06
    uw
    -0.06
     заÑħод
    -0.06
    FTA
    -0.06
     anyone
    -0.06
    podob
    -0.06
    POSITIVE LOGITS
    Scene
    0.08
    ilogue
    0.07
    anye
    0.07
     Scene
    0.07
     scene
    0.07
    actus
    0.07
    atchet
    0.07
    ernes
    0.06
     sonunda
    0.06
     Act
    0.06
    Activations Density 0.001%

    No Known Activations