© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 16940
    Prev
    Next
    INDEX
    Explanations

    emotional and ethical issues within narratives, particularly related to social justice and human rights

    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
    551
    -0.06
    ifa
    -0.06
    sei
    -0.06
    th
    -0.06
    kos
    -0.06
    bang
    -0.06
    éĥ
    -0.06
    kus
    -0.05
     frequent
    -0.05
     tÄĽch
    -0.05
    POSITIVE LOGITS
    utura
    0.07
    tega
    0.07
    anta
    0.07
    ento
    0.06
    е
    0.06
     Weiss
    0.06
    afort
    0.06
    Ñģ
    0.06
    etur
    0.06
     Ñģ
    0.06
    Activations Density 0.071%

    No Known Activations