© 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 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. 16498
    Prev
    Next
    INDEX
    Explanations

    words related to legality or regulatory issues

    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
    ottes
    -0.07
    levard
    -0.07
    elier
    -0.07
    ady
    -0.06
    y
    -0.06
    intree
    -0.06
    ise
    -0.06
    fy
    -0.06
    uld
    -0.06
     Fol
    -0.06
    POSITIVE LOGITS
    /***/
    0.07
    _VM
    0.07
    icie
    0.06
     rag
    0.06
    ãĤ¶ãĥ¼
    0.06
    _GF
    0.06
     mach
    0.06
    å®
    0.06
    BackPressed
    0.06
     VÅ¡
    0.06
    Activations Density 0.001%

    No Known Activations