© 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. 1700
    Prev
    Next
    INDEX
    Explanations

    instructions related to the use and removal of materials

    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
     dio
    -0.06
    illes
    -0.06
     å
    -0.06
    ernote
    -0.06
    open
    -0.06
    TRA
    -0.06
     mist
    -0.05
    ico
    -0.05
    _fatal
    -0.05
    èİ
    -0.05
    POSITIVE LOGITS
     оÑĤли
    0.08
     stuck
    0.08
     easier
    0.07
     adher
    0.07
     lift
    0.07
     pulling
    0.07
    Indented
    0.07
    lift
    0.06
     Lift
    0.06
     adherence
    0.06
    Activations Density 0.022%

    No Known Activations