Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95863
    Prev
    Next
    INDEX
    Explanations

    mentions of specific geographical locations, particularly Wales

    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
    oux
    -0.08
    oen
    -0.07
    _distribution
    -0.06
    /title
    -0.06
    ogy
    -0.06
    oble
    -0.06
    abit
    -0.06
    objective
    -0.06
     objective
    -0.06
    ationToken
    -0.06
    POSITIVE LOGITS
    ãĥ¼ãĥª
    0.07
    ynet
    0.07
    deÅŁ
    0.06
     strap
    0.06
     Morr
    0.06
    alia
    0.06
     Rif
    0.06
    strap
    0.06
    ruž
    0.06
    ISTER
    0.06
    Activations Density 0.000%

    No Known Activations