© 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. 30-LLAMASCOPE-RES-32K
    11. 9541
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     âĤ¹
    -0.16
     createSelector
    -0.14
     subsequ
    -0.14
    ihn
    -0.13
    глÑıд
    -0.13
    èĸ¬
    -0.13
    CppClass
    -0.13
    ingleton
    -0.13
    åijĬ
    -0.13
    олÑĮно
    -0.12
    POSITIVE LOGITS
     rab
    0.35
     Rab
    0.30
     Rabbi
    0.29
    rab
    0.29
     Judaism
    0.27
     rabbits
    0.26
     Jewish
    0.26
     Jews
    0.25
     synagogue
    0.24
     rabbit
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.