© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 59672
    Prev
    Next
    INDEX
    Explanations

    HTML form elements and button actions

    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
     Yosh
    -0.07
     Anders
    -0.06
     Owens
    -0.06
    atori
    -0.06
     Thi
    -0.06
     Ãľl
    -0.06
     Sender
    -0.06
    BÆ°á»Ľc
    -0.06
    .Writer
    -0.06
     Suzuki
    -0.05
    POSITIVE LOGITS
    eger
    0.09
    εια
    0.07
    eriod
    0.07
    argo
    0.07
    ureka
    0.07
    ovo
    0.07
    chio
    0.06
    peri
    0.06
    _outline
    0.06
    nullable
    0.06
    Activations Density 0.010%

    No Known Activations