© 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. 76531
    Prev
    Next
    INDEX
    Explanations

    references to chat rooms or online chatting features

    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
    loff
    -0.07
     pattern
    -0.07
    ena
    -0.06
    lav
    -0.06
     active
    -0.06
     Gil
    -0.06
     vit
    -0.06
     pand
    -0.06
     ramp
    -0.06
    ENA
    -0.05
    POSITIVE LOGITS
    ingles
    0.07
    GMEM
    0.07
    구
    0.06
    haf
    0.06
    /tinyos
    0.06
    hod
    0.06
    imli
    0.06
    боÑĤ
    0.06
    ektör
    0.06
    SCII
    0.06
    Activations Density 0.000%

    No Known Activations