© 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. 58988
    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
     (
    -0.07
     –
    -0.06
     &
    -0.06
     —
    -0.06
     [
    -0.06
     --
    -0.06
     "
    -0.06
    ansi
    -0.06
    ens
    -0.06
    J
    -0.06
    POSITIVE LOGITS
    äl
    0.09
     handjob
    0.09
    luv
    0.09
    аÑĤок
    0.08
    .scalablytyped
    0.08
    //**↵
    0.08
    elon
    0.08
    LOAT
    0.08
    æ¢
    0.08
    ีà¹Ģà¸Ķ
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.