© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 55763
    Prev
    Next
    INDEX
    Explanations

    phrases related to online engagement and community involvement

    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
    .camel
    -0.07
    allet
    -0.07
    ì§ij
    -0.07
    å¦
    -0.06
    ovit
    -0.06
    .clock
    -0.06
    :checked
    -0.06
    /context
    -0.06
    ago
    -0.06
    ogan
    -0.06
    POSITIVE LOGITS
    chor
    0.09
     mailing
    0.09
     ranks
    0.08
    bei
    0.07
     chorus
    0.07
     Telegram
    0.06
    Telegram
    0.06
    unsubscribe
    0.06
    Mui
    0.06
     conversation
    0.06
    Activations Density 0.014%

    No Known Activations