© 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. 40963
    Prev
    Next
    INDEX
    Explanations

    instructions and steps related to technical processes or configurations

    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
     HOLDER
    -0.07
    addir
    -0.07
    azor
    -0.07
     fus
    -0.07
    itä
    -0.06
    çª
    -0.06
     burn
    -0.06
    mdir
    -0.06
    lav
    -0.06
     Ost
    -0.06
    POSITIVE LOGITS
     select
    0.08
     choose
    0.08
    select
    0.08
     вÑĭбиÑĢа
    0.07
     selects
    0.07
     then
    0.07
    then
    0.07
    nder
    0.07
    357
    0.07
     chose
    0.07
    Activations Density 0.010%

    No Known Activations