© 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. 86433
    Prev
    Next
    INDEX
    Explanations

    references to archived materials or events

    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
    ovich
    -0.07
    å²Ĺ
    -0.06
     hole
    -0.06
    anax
    -0.06
     holes
    -0.06
     Imag
    -0.05
    an
    -0.05
    nez
    -0.05
    ovy
    -0.05
     qu
    -0.05
    POSITIVE LOGITS
    -original
    0.09
     оÑĢиг
    0.09
     original
    0.09
     originals
    0.09
     původ
    0.08
    аÑĢÑĩ
    0.08
    original
    0.08
    /original
    0.08
    åİŁå§ĭ
    0.08
    (original
    0.07
    Activations Density 0.001%

    No Known Activations