© 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. 4633
    Prev
    Next
    INDEX
    Explanations

    references to political bias and accountability within law enforcement agencies

    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
    $__
    -0.08
    _GF
    -0.08
    fono
    -0.07
     JSX
    -0.07
    ¼
    -0.07
    rowad
    -0.07
    resi
    -0.07
    Overrides
    -0.07
    endir
    -0.07
    gregar
    -0.07
    POSITIVE LOGITS
     bias
    0.08
     Bias
    0.08
     DC
    0.07
     Mish
    0.06
     impartial
    0.06
    oval
    0.06
     Steele
    0.06
     Ant
    0.06
     shared
    0.05
    Bias
    0.05
    Activations Density 0.004%

    No Known Activations