© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 79086
    Prev
    Next
    INDEX
    Explanations

    references to government-related financial aid and contributions

    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
     Shapiro
    -0.06
     lateral
    -0.06
    ippy
    -0.06
    alex
    -0.06
     shall
    -0.06
     global
    -0.06
    gota
    -0.05
    Inject
    -0.05
    lob
    -0.05
     pay
    -0.05
    POSITIVE LOGITS
    'gc
    0.08
    åįļçī©
    0.08
    STALL
    0.08
    ائب
    0.08
    елÑĮзÑı
    0.08
    immel
    0.07
    CLAIM
    0.07
     bầu
    0.07
    .gc
    0.07
    NCY
    0.07
    Activations Density 0.002%

    No Known Activations