© 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. 124929
    Prev
    Next
    INDEX
    Explanations

    sections of text formatted as code or technical content

    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
    HeaderValue
    -0.09
    isté
    -0.08
    ستر
    -0.07
    //{{
    -0.07
    iac
    -0.07
    #
    -0.07
    strup
    -0.07
    iability
    -0.07
    enums
    -0.06
    roat
    -0.06
    POSITIVE LOGITS
     Bid
    0.06
     rushes
    0.06
     amat
    0.05
     cutting
    0.05
     Fe
    0.05
    aro
    0.05
     صÙĨع
    0.05
     Soros
    0.05
    \d
    0.05
     chắn
    0.05
    Activations Density 0.000%

    No Known Activations