© 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. 15-LLAMASCOPE-RES-131K
    11. 61979
    Prev
    Next
    INDEX
    Explanations

    narratives and personal testimonies related to social issues, particularly those affecting marginalized communities

    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
     huz
    -0.08
    iol
    -0.07
    ToPoint
    -0.07
    жд
    -0.07
    æĭ¥
    -0.07
    otros
    -0.07
     skl
    -0.07
    å±±å¸Ĥ
    -0.07
    ENA
    -0.07
    ãĤ¤ãĥī
    -0.07
    POSITIVE LOGITS
     anonym
    0.08
     stories
    0.07
     voices
    0.07
    stories
    0.07
     case
    0.07
     individual
    0.07
     voice
    0.06
    raits
    0.06
    Stories
    0.06
    REAL
    0.06
    Activations Density 0.042%

    No Known Activations