© 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. 58505
    Prev
    Next
    INDEX
    Explanations

    numerical data related to demographics and geographical information

    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
    acf
    -0.06
    umont
    -0.06
    rome
    -0.06
    HE
    -0.06
    ãģ¾ãĤĬ
    -0.06
    andom
    -0.05
     specifications
    -0.05
     butcher
    -0.05
    771
    -0.05
     ill
    -0.05
    POSITIVE LOGITS
    asca
    0.08
    /GPL
    0.07
    iving
    0.07
    æĭ¬
    0.07
    ocs
    0.07
    bourg
    0.07
    ãĥ¼ãĥį
    0.07
    jist
    0.07
    ?q
    0.07
     olma
    0.07
    Activations Density 0.001%

    No Known Activations