© 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. 3712
    Prev
    Next
    INDEX
    Explanations

    references to bans or prohibitions related to various topics

    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
    ugg
    -0.07
    éĩįçĤ¹
    -0.07
    _firestore
    -0.07
    ırak
    -0.06
    ä¸įæĸŃ
    -0.06
    elu
    -0.06
    zan
    -0.06
    Nu
    -0.06
    ikki
    -0.06
     оÑĤвеÑĢ
    -0.06
    POSITIVE LOGITS
     use
    0.09
    ozem
    0.08
    AllWindows
    0.07
    zyst
    0.07
     anyone
    0.07
    ovky
    0.07
    ish
    0.07
     altogether
    0.06
    å¤ķ
    0.06
     Use
    0.06
    Activations Density 0.023%

    No Known Activations