© 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. 77996
    Prev
    Next
    INDEX
    Explanations

    terms related to responsibility and ethical practices 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
    ChangeEvent
    -0.08
    lage
    -0.07
    580
    -0.07
    ASE
    -0.06
    .idea
    -0.06
    oÄį
    -0.06
    oba
    -0.06
     tÃŃm
    -0.06
    enate
    -0.06
    Reach
    -0.06
    POSITIVE LOGITS
     manner
    0.09
    ness
    0.09
     conduct
    0.08
     practices
    0.08
     ness
    0.08
    NESS
    0.08
     Practices
    0.07
     way
    0.07
    conduct
    0.07
    erd
    0.07
    Activations Density 0.033%

    No Known Activations