© 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. 128647
    Prev
    Next
    INDEX
    Explanations

    verbs related to emotional engagement and states of being

    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
    brig
    -0.06
    AAF
    -0.06
    жд
    -0.06
     dán
    -0.06
    eland
    -0.06
    Dynamic
    -0.06
    kara
    -0.06
    preter
    -0.06
    aeper
    -0.06
    kf
    -0.06
    POSITIVE LOGITS
     Chambers
    0.07
    ersh
    0.06
    angelo
    0.06
    sip
    0.06
     rid
    0.06
    oler
    0.06
    empl
    0.06
    ï¼¥
    0.06
    ή
    0.06
    376
    0.06
    Activations Density 0.029%

    No Known Activations