© 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. 40165
    Prev
    Next
    INDEX
    Explanations

    phrases related to retirement and ideal living conditions

    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
    razier
    -0.07
    taÅŁ
    -0.07
    Äįek
    -0.07
    emez
    -0.07
     ÄĮer
    -0.07
    essler
    -0.07
    egend
    -0.07
     èŤ
    -0.07
    usher
    -0.07
    ICY
    -0.06
    POSITIVE LOGITS
    ÑĨо
    0.06
    closure
    0.06
    Escape
    0.06
     pedestal
    0.06
     BOT
    0.06
     ast
    0.06
    638
    0.06
    rok
    0.06
     Overrides
    0.06
    .AR
    0.06
    Activations Density 0.035%

    No Known Activations