© 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. 40824
    Prev
    Next
    INDEX
    Explanations

    words that convey curiosity or irony

    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
     sao
    -0.08
    Äįi
    -0.07
    Ïĥιο
    -0.07
    nero
    -0.07
    ught
    -0.07
    overe
    -0.07
    stry
    -0.07
    eson
    -0.07
    anian
    -0.06
    ždy
    -0.06
    POSITIVE LOGITS
     speaking
    0.08
    ingly
    0.07
     none
    0.07
    ,
    0.07
    dül
    0.07
    none
    0.06
    (?
    0.06
    Insp
    0.06
     neither
    0.06
     no
    0.06
    Activations Density 0.007%

    No Known Activations