© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 3040
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    /INFO
    -0.06
    riere
    -0.06
    antu
    -0.06
     báºŃc
    -0.06
     stere
    -0.06
    istra
    -0.06
     Heck
    -0.05
    wt
    -0.05
     my
    -0.05
    наÑĩе
    -0.05
    POSITIVE LOGITS
     fucked
    0.10
     fucking
    0.09
     fucks
    0.08
     handjob
    0.08
     Fucking
    0.08
     cunt
    0.08
     FUCK
    0.07
     fuck
    0.07
     Fuck
    0.07
     bullshit
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.