© 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. 15-LLAMASCOPE-RES-131K
    11. 88445
    Prev
    Next
    INDEX
    Explanations

    names of political figures and references to political commentary

    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
    ÑģÑĤи
    -0.08
    _mi
    -0.07
    abbr
    -0.07
    940
    -0.07
    iband
    -0.06
    rosso
    -0.06
    ood
    -0.06
    ssa
    -0.06
    lac
    -0.06
    leccion
    -0.06
    POSITIVE LOGITS
    rido
    0.08
    strom
    0.08
    CD
    0.07
     vej
    0.06
    aley
    0.06
    ridge
    0.06
    deck
    0.06
    embro
    0.06
     khoa
    0.06
     Koch
    0.06
    Activations Density 0.011%

    No Known Activations