© 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. 87427
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to various studies or analyses

    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
    IFO
    -0.07
    leon
    -0.07
    ìĿį
    -0.07
    eyer
    -0.06
    ritch
    -0.06
    ATTER
    -0.06
    emey
    -0.06
    Äĥn
    -0.06
    koneksi
    -0.06
    TextStyle
    -0.06
    POSITIVE LOGITS
     alike
    0.10
    /etc
    0.08
     combo
    0.07
    ropol
    0.07
    argout
    0.07
    iec
    0.06
    /tos
    0.06
    iske
    0.06
     respectively
    0.06
    uai
    0.06
    Activations Density 0.010%

    No Known Activations