© 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. 3830
    Prev
    Next
    INDEX
    Explanations

    references to film distribution and related controversies

    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
     capture
    -0.06
    utomation
    -0.06
     Stam
    -0.06
    _Grid
    -0.06
    oss
    -0.06
    ToolStrip
    -0.06
    ÙĨØ´
    -0.06
    vac
    -0.06
     vacations
    -0.06
     ÎĬ
    -0.06
    POSITIVE LOGITS
     censorship
    0.08
     preview
    0.07
    antino
    0.07
    åİŁæľ¬
    0.07
    llib
    0.07
    iego
    0.07
    @dynamic
    0.06
     censor
    0.06
    flammatory
    0.06
     Content
    0.06
    Activations Density 0.007%

    No Known Activations