© 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. 93441
    Prev
    Next
    INDEX
    Explanations

    URLs and web links

    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
    uner
    -0.07
     arch
    -0.07
    /avatar
    -0.06
    otes
    -0.06
     mó
    -0.06
     Conserv
    -0.06
     Bannon
    -0.05
    ses
    -0.05
    ppers
    -0.05
    áÅĻ
    -0.05
    POSITIVE LOGITS
    youtu
    0.07
    duk
    0.07
    alara
    0.07
    velle
    0.07
    yre
    0.07
    kest
    0.07
    cae
    0.07
    GuidId
    0.06
    .linkedin
    0.06
    akra
    0.06
    Activations Density 0.016%

    No Known Activations