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

    Neuronpedia

    Jacobian LensNEW
    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. 78500
    Prev
    Next
    INDEX
    Explanations

    references to blame and accountability in various contexts

    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
    icari
    -0.08
    entai
    -0.07
    _TI
    -0.07
    اÙģÙĤ
    -0.07
    renc
    -0.07
    èĻij
    -0.07
    RLF
    -0.07
    PathParam
    -0.07
    ipel
    -0.07
    Overrides
    -0.07
    POSITIVE LOGITS
     blame
    0.23
     blaming
    0.19
     blames
    0.19
     blamed
    0.18
     responsibility
    0.16
    责任
    0.14
     Responsibility
    0.14
    責
    0.13
     respons
    0.12
    Respons
    0.12
    Activations Density 0.103%

    No Known Activations