© 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. 28907
    Prev
    Next
    INDEX
    Explanations

    references to travel restrictions related to Muslim individuals and countries

    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
     tast
    -0.07
     dile
    -0.07
    Trap
    -0.06
     CALLBACK
    -0.06
    uso
    -0.06
    Interceptor
    -0.06
    redits
    -0.06
    yleft
    -0.06
     Drop
    -0.06
    dro
    -0.06
    POSITIVE LOGITS
     Ci
    0.06
    asure
    0.06
    icipant
    0.06
    ÑĥмÑĥ
    0.06
    Operator
    0.06
    ewan
    0.06
     Laurie
    0.05
    .operator
    0.05
     facial
    0.05
    letic
    0.05
    Activations Density 0.007%

    No Known Activations