© 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. 129293
    Prev
    Next
    INDEX
    Explanations

    references to local businesses and community initiatives

    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
    /jav
    -0.07
    ctic
    -0.07
     javafx
    -0.07
    erot
    -0.07
    .ms
    -0.07
     vụ
    -0.07
    ÑĨип
    -0.07
     Freund
    -0.06
    ctal
    -0.06
    -urlencoded
    -0.06
    POSITIVE LOGITS
     Welsh
    0.18
     Wales
    0.16
     Cardiff
    0.13
     Swansea
    0.12
     Newport
    0.11
    Wel
    0.11
     Aber
    0.10
     Glam
    0.10
     Camb
    0.10
    Camb
    0.08
    Activations Density 0.063%

    No Known Activations