© 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. 124885
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages related to statistics or data

    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
    ersonic
    -0.07
    ëħĢ
    -0.07
    iciones
    -0.06
    umbn
    -0.06
    roje
    -0.06
    иж
    -0.06
    ÑĥменÑĤ
    -0.06
    ält
    -0.06
    ifact
    -0.06
     Scha
    -0.06
    POSITIVE LOGITS
    IBUTE
    0.07
    ron
    0.07
    abe
    0.07
    utow
    0.07
    edBy
    0.06
    jin
    0.06
    uga
    0.06
    }->{
    0.06
    iov
    0.06
     dil
    0.06
    Activations Density 0.023%

    No Known Activations