© 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. 41378
    Prev
    Next
    INDEX
    Explanations

    terms related to legal matters, particularly in the context of defamation and protections for individuals

    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
    Disposed
    -0.07
    oodle
    -0.07
    altar
    -0.06
    ovah
    -0.06
    @qq
    -0.06
    reesome
    -0.06
    alm
    -0.06
    adro
    -0.06
    odash
    -0.06
    ocene
    -0.06
    POSITIVE LOGITS
    ankind
    0.07
    380
    0.07
     worldwide
    0.06
    244
    0.06
     literature
    0.06
    AWN
    0.06
    cod
    0.06
    iene
    0.06
     lore
    0.06
    310
    0.05
    Activations Density 0.035%

    No Known Activations