© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-32K
    11. 19647
    Prev
    Next
    INDEX
    Explanations

    references to independent retail and local community activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agher
    -0.19
     americ
    -0.19
     american
    -0.19
     амеÑĢикан
    -0.18
     Americans
    -0.17
     American
    -0.17
    American
    -0.16
    arel
    -0.16
     اÙĦØ£ÙħرÙĬÙĥÙĬ
    -0.16
    ingo
    -0.15
    POSITIVE LOGITS
     England
    0.49
    England
    0.41
     UK
    0.41
     Britain
    0.40
     Scotland
    0.39
     Wales
    0.39
    UK
    0.37
    Britain
    0.33
    .uk
    0.31
     Yorkshire
    0.31
    Activations Density 0.102%

    No Known Activations