© 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 EvalsExportsinterp-engineNEWAPI 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. 80385
    Prev
    Next
    INDEX
    Explanations

    phrases related to human rights abuses

    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
    ensem
    -0.07
    麻
    -0.06
    ccione
    -0.06
    .fp
    -0.06
    agma
    -0.06
     circumference
    -0.06
     (^
    -0.06
    _losses
    -0.06
     crippling
    -0.06
    ResponseStatus
    -0.06
    POSITIVE LOGITS
     conditions
    0.13
     Conditions
    0.10
    Conditions
    0.10
    conditions
    0.09
     condiciones
    0.09
     CONDITIONS
    0.08
     living
    0.08
     condition
    0.08
     facilities
    0.08
    _conditions
    0.08
    Activations Density 0.048%

    No Known Activations