© 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. 5-LLAMASCOPE-RES-131K
    11. 126134
    Prev
    Next
    INDEX
    Explanations

    keywords related to life and death ethical dilemmas

    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
    íķij
    -0.08
    tail
    -0.07
    so
    -0.07
    serve
    -0.07
    kop
    -0.06
    omo
    -0.06
    ParameterValue
    -0.06
    sets
    -0.06
    ij
    -0.06
    боÑĤ
    -0.06
    POSITIVE LOGITS
    ylene
    0.06
     Yep
    0.06
    ilon
    0.06
    _SCL
    0.06
    iltr
    0.06
     Onion
    0.06
    lide
    0.06
    ÚĨÛĮ
    0.06
    ĵåIJį
    0.06
    382
    0.06
    Activations Density 0.000%

    No Known Activations