© 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 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. 59477
    Prev
    Next
    INDEX
    Explanations

    expressions of emotion and personal aspirations

    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
    idir
    -0.07
    åıĪ
    -0.07
     BOTH
    -0.06
     atleast
    -0.06
    adata
    -0.06
    ichel
    -0.06
    Both
    -0.06
    acie
    -0.06
     instead
    -0.06
    itoris
    -0.06
    POSITIVE LOGITS
     necessarily
    0.13
     directly
    0.11
     actual
    0.11
     exact
    0.11
     specifically
    0.09
     pÅĻÃŃmo
    0.09
     immediately
    0.09
     exactly
    0.09
     Actual
    0.08
     DIRECT
    0.08
    Activations Density 0.058%

    No Known Activations