© 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. 71032
    Prev
    Next
    INDEX
    Explanations

    references to Justin Bieber and associations with controversies or negative incidents

    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
     cancers
    -0.07
     remar
    -0.07
    çµ
    -0.07
    SELL
    -0.07
    _fb
    -0.07
    abra
    -0.06
    %p
    -0.06
     mast
    -0.06
    FB
    -0.06
     æ¬
    -0.06
    POSITIVE LOGITS
    DM
    0.08
    ior
    0.07
    iales
    0.07
     DM
    0.07
    etto
    0.07
    apon
    0.06
    è
    0.06
    endor
    0.06
    MT
    0.06
     Backup
    0.06
    Activations Density 0.004%

    No Known Activations