© 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. 2443
    Prev
    Next
    INDEX
    Explanations

    words associated with safety and security

    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
     caravan
    -0.06
    ment
    -0.06
    amura
    -0.06
     recognition
    -0.05
     antis
    -0.05
     quint
    -0.05
     Obt
    -0.05
     Arena
    -0.05
    optim
    -0.05
     recognized
    -0.05
    POSITIVE LOGITS
    åłĤ
    0.07
    .tsv
    0.07
     McMaster
    0.07
    actable
    0.07
    _Cmd
    0.07
    Indented
    0.07
    ãĥ¼ãĥŀ
    0.07
    Ñħов
    0.07
    imu
    0.07
    dsa
    0.07
    Activations Density 0.000%

    No Known Activations