© 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. 15-LLAMASCOPE-RES-131K
    11. 26934
    Prev
    Next
    INDEX
    Explanations

    phrases related to booking and reservation policies

    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
    kaz
    -0.07
     Roch
    -0.06
    rez
    -0.06
     Král
    -0.06
    archy
    -0.06
    kÄĻ
    -0.06
     stream
    -0.06
    itch
    -0.06
    933
    -0.05
     Legend
    -0.05
    POSITIVE LOGITS
    inode
    0.08
    ONLY
    0.08
    μαÏĦο
    0.07
    TER
    0.07
    .bunifuFlatButton
    0.07
    .updateDynamic
    0.07
    TERS
    0.07
    Ïħγ
    0.07
    daki
    0.07
    .scalablytyped
    0.07
    Activations Density 0.018%

    No Known Activations