© 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. 118907
    Prev
    Next
    INDEX
    Explanations

    words related to suffering and moral issues

    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
    çĦ¡ãģĹ
    -0.07
    agara
    -0.06
     somew
    -0.06
    ба
    -0.06
    787
    -0.06
    EATURE
    -0.06
    ORIZONTAL
    -0.06
    ginas
    -0.06
    лив
    -0.06
    iliz
    -0.06
    POSITIVE LOGITS
     nons
    0.07
    iez
    0.07
    )prepare
    0.07
    .Accessible
    0.06
    ноз
    0.06
    ç
    0.06
    éļ
    0.06
    áj
    0.06
    iyon
    0.06
    á»ĩu
    0.06
    Activations Density 0.000%

    No Known Activations