© 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. 76018
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    arness
    -0.07
    anic
    -0.06
    ServiceImpl
    -0.06
    oz
    -0.05
    s
    -0.05
    anos
    -0.05
    guide
    -0.05
    aver
    -0.05
    astes
    -0.05
    form
    -0.05
    POSITIVE LOGITS
    Ùĩا
    0.08
    oten
    0.07
    chas
    0.07
    .obtain
    0.07
    /disable
    0.07
    ÏĥÏĩ
    0.07
    krom
    0.07
    _extended
    0.07
    ız
    0.07
    ragen
    0.07
    Activations Density 0.001%

    No Known Activations