© 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. 70456
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a procedure or set of instructions

    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
     AVC
    -0.07
    hod
    -0.07
    hood
    -0.07
    hud
    -0.07
    sonian
    -0.07
    kop
    -0.07
    asal
    -0.07
    .construct
    -0.07
    asaki
    -0.07
    POSITIVE LOGITS
     follows
    0.08
    cert
    0.07
     below
    0.06
     seguint
    0.06
    EndElement
    0.06
     novel
    0.06
     ëĭ¤ìĿĮê³¼
    0.06
     MaterialApp
    0.06
    ëĵľë¦¬
    0.06
    å¾Ģ
    0.05
    Activations Density 0.007%

    No Known Activations