© 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. 3292
    Prev
    Next
    INDEX
    Explanations

    language related to job applications and employer expectations

    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
    AQ
    -0.07
     åĿ
    -0.07
    еÑģи
    -0.07
    'gc
    -0.07
    dech
    -0.06
    hangi
    -0.06
     Incontri
    -0.06
    leurs
    -0.06
    ë¬
    -0.06
    .opens
    -0.06
    POSITIVE LOGITS
    gabe
    0.06
    setDisplay
    0.06
    ustos
    0.06
     conver
    0.06
    дÑĥ
    0.06
     exactly
    0.06
    zend
    0.06
    fos
    0.06
    IPH
    0.06
    acer
    0.05
    Activations Density 0.000%

    No Known Activations