© 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. 55609
    Prev
    Next
    INDEX
    Explanations

    sections of code, specifically focusing on function definitions and structural elements

    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
    ABI
    -0.07
    abi
    -0.07
    hoc
    -0.07
     Defender
    -0.06
    ÑģÑĤÑĢÑĥ
    -0.06
    ikk
    -0.06
    vore
    -0.06
    ilon
    -0.06
    idges
    -0.05
    tk
    -0.05
    POSITIVE LOGITS
    ĶåĽŀ
    0.07
    RELATED
    0.06
    æģµ
    0.06
     Feather
    0.06
    addons
    0.06
    posix
    0.06
    ald
    0.06
    .MouseAdapter
    0.06
    _EDITOR
    0.06
     NEO
    0.06
    Activations Density 0.001%

    No Known Activations