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

    Neuronpedia

    Jacobian LensNEW
    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. 31-LLAMASCOPE-RES-32K
    11. 20045
    Prev
    Next
    INDEX
    Explanations

    elements and properties related to data structures and policies in coding or configuration contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    [âĢ¦]
    -0.23
    (['
    -0.22
    (["
    -0.20
    ]['
    -0.20
    ([]
    -0.20
    ("
    -0.20
    "]["
    -0.20
    ([[
    -0.19
    ]["
    -0.19
    [][]
    -0.19
    POSITIVE LOGITS
     [
    0.56
    afone
    0.18
    istrovstvÃŃ
    0.17
    ekil
    0.17
     *[
    0.17
     `[
    0.16
    @nate
    0.16
     //[
    0.16
    __[
    0.16
    -[
    0.16
    Activations Density 0.043%

    No Known Activations