© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90445
    Prev
    Next
    INDEX
    Explanations

    elements related to CSS styling attributes

    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
    aksi
    -0.08
    縮
    -0.07
    ADER
    -0.07
    loser
    -0.07
    _Static
    -0.07
    สà¸Ļ
    -0.07
    iseum
    -0.07
    aset
    -0.07
    ynet
    -0.07
    ãģĵãĤį
    -0.06
    POSITIVE LOGITS
    488
    0.07
    itu
    0.06
    639
    0.06
    640
    0.06
    aldi
    0.06
    elas
    0.05
    631
    0.05
    land
    0.05
    eliness
    0.05
    amine
    0.05
    Activations Density 0.000%

    No Known Activations