© 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. 9-LLAMASCOPE-RES-131K
    11. 97062
    Prev
    Next
    INDEX
    Explanations

    quantitative statistics related to housing or population metrics

    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
     latter
    -0.08
    hai
    -0.07
     Homo
    -0.07
    ito
    -0.07
    umen
    -0.06
    nym
    -0.06
    bak
    -0.06
    à¸Ĭาà¸ķ
    -0.06
    BlockSize
    -0.06
    556
    -0.06
    POSITIVE LOGITS
    ibble
    0.08
    ASA
    0.08
    uffix
    0.07
    -tm
    0.07
    ollar
    0.07
    ãĤµãĥ¼
    0.07
    adia
    0.07
    orners
    0.07
    avez
    0.07
    redients
    0.07
    Activations Density 0.038%

    No Known Activations