© 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. 29527
    Prev
    Next
    INDEX
    Explanations

    references to human flaws and the complexities of relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text discussing human nature, emphasizing that people or characters have human qualities, flaws, vulnerabilities, and imperfections.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ÏĦÏģο
    -0.07
     Guardians
    -0.06
    yas
    -0.06
     Corn
    -0.06
    ört
    -0.06
    kus
    -0.06
    orgia
    -0.06
     Brun
    -0.06
    arde
    -0.06
     Baum
    -0.06
    POSITIVE LOGITS
     human
    0.22
    human
    0.19
    -human
    0.19
     Human
    0.16
    Human
    0.16
     humans
    0.16
    _human
    0.15
    UMAN
    0.14
     Humans
    0.13
     humano
    0.13
    Activations Density 0.078%

    No Known Activations