© 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. 16203
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal rights and prohibitions

    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
    agos
    -0.09
    IDEO
    -0.08
    lore
    -0.08
    ystick
    -0.07
    ExecutionContext
    -0.07
    	ERROR
    -0.07
     limburg
    -0.07
    UG
    -0.07
    QRST
    -0.07
    åľ¨çº¿è§Ĩé¢ij
    -0.07
    POSITIVE LOGITS
     any
    0.08
     ANY
    0.06
     nor
    0.06
     anything
    0.06
     discrimination
    0.06
    nor
    0.06
     Nor
    0.06
    Nor
    0.06
    Any
    0.06
     anymore
    0.06
    Activations Density 0.017%

    No Known Activations