© 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. 88639
    Prev
    Next
    INDEX
    Explanations

    references to risk or threat

    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
    лÑı
    -0.07
    ãģ¡ãĤĩ
    -0.07
    pdb
    -0.07
    -ing
    -0.07
    IFI
    -0.07
    enge
    -0.06
    å±
    -0.06
    clamp
    -0.06
    strcasecmp
    -0.06
    ERY
    -0.06
    POSITIVE LOGITS
    ously
    0.10
    ous
    0.09
    -danger
    0.09
    éļª
    0.07
    133
    0.07
    stell
    0.07
    oust
    0.07
    lijke
    0.06
    /security
    0.06
    avigation
    0.06
    Activations Density 0.013%

    No Known Activations