© 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. 79733
    Prev
    Next
    INDEX
    Explanations

    formal policy-related language

    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
     tar
    -0.07
    /cgi
    -0.06
    quo
    -0.06
    tar
    -0.06
    è£
    -0.06
    ailed
    -0.06
    æķ¦
    -0.06
    æļ®
    -0.06
    Inspect
    -0.06
     au
    -0.06
    POSITIVE LOGITS
     policy
    0.18
     policies
    0.16
     Policy
    0.15
    policy
    0.15
     Policies
    0.14
    Policy
    0.14
    _policy
    0.13
    (policy
    0.13
    olicy
    0.12
    æĶ¿çŃĸ
    0.12
    Activations Density 0.147%

    No Known Activations