© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 104091
    Prev
    Next
    INDEX
    Explanations

    references to remakes and adaptations of films or shows

    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
     Quentin
    -0.07
    .Companion
    -0.07
    æľĭ
    -0.07
    ##_
    -0.07
    elor
    -0.06
    upported
    -0.06
    cac
    -0.06
    оÑĢд
    -0.06
     Spray
    -0.06
     temporary
    -0.06
    POSITIVE LOGITS
    enko
    0.09
    ovsky
    0.07
    rem
    0.07
     remake
    0.07
     rem
    0.07
    368
    0.07
    367
    0.07
     Original
    0.06
     identical
    0.06
    original
    0.06
    Activations Density 0.010%

    No Known Activations