© 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. 39540
    Prev
    Next
    INDEX
    Explanations

    phrases that convey contrasting narratives or perspectives on identity and belonging

    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
     Preis
    -0.07
    Dans
    -0.07
    emm
    -0.07
    odus
    -0.06
    bourg
    -0.06
     Associate
    -0.06
    aska
    -0.06
    asil
    -0.06
    erts
    -0.06
    ulis
    -0.06
    POSITIVE LOGITS
    Them
    0.07
     them
    0.07
     Morrow
    0.07
    ãģĤãģ®
    0.07
     theirs
    0.06
    autos
    0.06
     fet
    0.06
     Them
    0.06
    them
    0.06
     ним
    0.06
    Activations Density 0.028%

    No Known Activations