© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 12-LLAMASCOPE-RES-32K
    11. 6380
    Prev
    Next
    INDEX
    Explanations

    product availability and features related to food and nutrition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    APA
    -0.17
    ultipartFile
    -0.15
    ings
    -0.15
    esp
    -0.14
     bev
    -0.14
    éº
    -0.14
    allee
    -0.14
    rzy
    -0.14
    kea
    -0.13
    avs
    -0.13
    POSITIVE LOGITS
     whereas
    0.21
     Whereas
    0.17
    uzzi
    0.14
    aram
    0.14
    utto
    0.14
    VOID
    0.14
     diff
    0.14
    ummer
    0.14
    ots
    0.13
     ÙĤب
    0.13
    Activations Density 0.273%

    No Known Activations