© 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. 71049
    Prev
    Next
    INDEX
    Explanations

    references to office spaces and related environments

    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
    ners
    -0.07
    wit
    -0.07
    ноз
    -0.07
    soever
    -0.07
    ming
    -0.07
    NotificationCenter
    -0.07
    /oct
    -0.06
    oral
    -0.06
     obvious
    -0.06
    elp
    -0.06
    POSITIVE LOGITS
    365
    0.09
    ehler
    0.07
    lique
    0.07
    -hours
    0.07
    ÙĤات
    0.07
    beat
    0.07
    stry
    0.07
    lament
    0.06
     '\''
    0.06
    loads
    0.06
    Activations Density 0.023%

    No Known Activations