© 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. 119482
    Prev
    Next
    INDEX
    Explanations

    references to character interactions and appearances in a narrative

    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
    ldr
    -0.07
     seins
    -0.07
    -mouth
    -0.07
    hiba
    -0.07
    综åIJĪ
    -0.07
    phia
    -0.06
    _mB
    -0.06
    å§Ĭ
    -0.06
    _mE
    -0.06
    lep
    -0.06
    POSITIVE LOGITS
     characters
    0.13
    characters
    0.10
     character
    0.10
     Characters
    0.10
     personalities
    0.09
     cast
    0.09
     introduced
    0.08
     introdu
    0.08
    Characters
    0.08
    .characters
    0.08
    Activations Density 0.042%

    No Known Activations