© 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. 92938
    Prev
    Next
    INDEX
    Explanations

    references to fascism and its associated terms

    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
    herits
    -0.07
    eper
    -0.07
    anks
    -0.07
    enting
    -0.07
    ez
    -0.07
    виÑĩай
    -0.06
    ales
    -0.06
    lopen
    -0.06
    esh
    -0.06
    onavir
    -0.06
    POSITIVE LOGITS
    çĤİ
    0.07
     fac
    0.07
    ulumi
    0.07
     Fac
    0.07
    fac
    0.07
    gel
    0.07
    ination
    0.06
    inating
    0.06
    @Web
    0.06
    bones
    0.06
    Activations Density 0.006%

    No Known Activations