© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 96436
    Prev
    Next
    INDEX
    Explanations

    quantitative data and statistics related to large numbers

    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
    shaw
    -0.07
    .scalablytyped
    -0.07
    ufen
    -0.07
    éĢ£
    -0.07
    ynomial
    -0.07
    ftar
    -0.07
    ei
    -0.06
    /Typography
    -0.06
    childs
    -0.06
    ouble
    -0.06
    POSITIVE LOGITS
     proced
    0.07
    //{{
    0.06
     Levy
    0.06
    .px
    0.06
    λεκ
    0.06
    rosse
    0.06
     Twe
    0.06
    .Cond
    0.06
    inho
    0.06
    é¼
    0.06
    Activations Density 0.036%

    No Known Activations