© 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 EvalsExportsinterp-engineNEWAPI 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. 41424
    Prev
    Next
    INDEX
    Explanations

    demonstrative pronouns and adjectives indicating preference or appreciation

    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
     -
    -0.07
     –
    -0.06
     :
    -0.06
     (
    -0.06
    emma
    -0.06
     whose
    -0.06
    iv
    -0.06
     KD
    -0.06
     ,
    -0.05
    :
    -0.05
    POSITIVE LOGITS
    #ad
    0.09
    ãĥ¼ãĥª
    0.09
    aÅĻ
    0.08
    anik
    0.08
    undle
    0.08
    ssc
    0.08
     BirliÄŁi
    0.07
    larınız
    0.07
    angen
    0.07
    teri
    0.07
    Activations Density 0.009%

    No Known Activations