© 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. 127041
    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
    _INLINE
    -0.08
     eldre
    -0.08
     apprec
    -0.07
    Â
    -0.07
    tempt
    -0.06
    éri
    -0.06
    cestor
    -0.06
    ored
    -0.06
     humble
    -0.06
    lef
    -0.06
    POSITIVE LOGITS
    úc
    0.06
     Catholic
    0.06
     Catholics
    0.06
     fucked
    0.06
    dehy
    0.06
    ãĥ¼ãĥĨãĤ£
    0.06
    é¨
    0.06
     catholic
    0.06
    gaard
    0.06
     Honor
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.