© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 38589
    Prev
    Next
    INDEX
    Explanations

    negative terms or phrases related to restrictions and prohibitions

    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
    entiful
    -0.06
    oming
    -0.06
    893
    -0.06
     Ca
    -0.06
     defe
    -0.05
    eba
    -0.05
     nhau
    -0.05
    ful
    -0.05
    .ce
    -0.05
    iale
    -0.05
    POSITIVE LOGITS
    působ
    0.07
    uml
    0.07
    ernals
    0.07
    rut
    0.07
    esel
    0.07
    endum
    0.07
    UBLE
    0.07
    ÑĢÑĥкÑĤ
    0.06
     ark
    0.06
    ark
    0.06
    Activations Density 0.008%

    No Known Activations