© 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. 62914
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal ownership or attribution

    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
    anz
    -0.06
     elderly
    -0.06
    anc
    -0.06
    ErrorMessage
    -0.06
    isel
    -0.06
    PIO
    -0.06
     adopt
    -0.05
    eway
    -0.05
     Fest
    -0.05
     Nest
    -0.05
    POSITIVE LOGITS
     bacheca
    0.08
    彡
    0.08
    347
    0.07
    ãĥ³ãĥĸ
    0.07
     herk
    0.07
     lately
    0.07
     매매ê°Ģ
    0.07
     hers
    0.07
    ubi
    0.07
    ë°ķ
    0.07
    Activations Density 0.000%

    No Known Activations