© 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. 76586
    Prev
    Next
    INDEX
    Explanations

    references to conservative political ideology

    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
    eger
    -0.08
    soever
    -0.08
    lé
    -0.07
    scribe
    -0.07
    lights
    -0.07
    vez
    -0.07
    lify
    -0.07
    lum
    -0.07
    illery
    -0.07
    åĦ¿
    -0.07
    POSITIVE LOGITS
    -leaning
    0.10
    allee
    0.08
    irts
    0.07
    /right
    0.07
    ardin
    0.07
    ischer
    0.06
    undle
    0.06
    /lib
    0.06
    ç·Ĵ
    0.06
    andler
    0.06
    Activations Density 0.011%

    No Known Activations