© 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. 28308
    Prev
    Next
    INDEX
    Explanations

    references to sources or citations related to literature and archival materials

    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
    ennon
    -0.07
    orna
    -0.07
    opher
    -0.07
    åŀ
    -0.07
    BootTest
    -0.07
    inas
    -0.06
    olon
    -0.06
    .="
    -0.06
    wing
    -0.06
     ÑģÑħод
    -0.06
    POSITIVE LOGITS
    تÙĬ
    0.06
    925
    0.06
     earm
    0.06
    üven
    0.06
    kek
    0.06
    ÑĻ
    0.06
    ÅĻet
    0.06
     Progressive
    0.06
     Demir
    0.06
    _reserve
    0.06
    Activations Density 0.004%

    No Known Activations