© 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. 87095
    Prev
    Next
    INDEX
    Explanations

    phrases related to respect and its importance in human interactions

    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
    icine
    -0.08
    rane
    -0.07
    usch
    -0.07
    upa
    -0.07
    оÑĹ
    -0.07
    antry
    -0.07
    sse
    -0.06
    onta
    -0.06
    ût
    -0.06
    elop
    -0.06
    POSITIVE LOGITS
    ably
    0.13
    ively
    0.12
    uously
    0.08
    ãģ¡ãģ¯
    0.08
    ately
    0.07
    ability
    0.07
    uous
    0.07
    full
    0.07
    SSION
    0.07
    ully
    0.07
    Activations Density 0.017%

    No Known Activations