© 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. 14-LLAMASCOPE-RES-32K
    6. 12959
    Prev
    Next
    INDEX
    Explanations

    names and references related to genealogy and family history

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibs
    -0.14
    кÑĢаÑĹн
    -0.14
    emp
    -0.14
     ëĮĢìĥģ
    -0.13
    .Dispose
    -0.13
    _HEADERS
    -0.13
     Tam
    -0.13
     al
    -0.13
    Translator
    -0.13
     Garden
    -0.13
    POSITIVE LOGITS
     Historical
    0.17
     cust
    0.15
    imeline
    0.15
     historical
    0.14
    iline
    0.14
     gene
    0.14
     historians
    0.14
     historian
    0.14
     maiden
    0.14
    ÑĮко
    0.14
    Activations Density 0.142%

    No Known Activations