© 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. 4-LLAMASCOPE-RES-32K
    11. 28906
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to file inclusion and execution within code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aina
    -0.18
    ÂŁ
    -0.14
    asher
    -0.14
    λη
    -0.14
    oog
    -0.14
    éľ²
    -0.13
     Innoc
    -0.13
    doctrine
    -0.13
    amus
    -0.13
    ModelError
    -0.13
    POSITIVE LOGITS
    eyim
    0.18
    prav
    0.17
    eyin
    0.15
    isky
    0.15
    æ¢
    0.14
    inton
    0.14
    人æīį
    0.14
    dsl
    0.14
    ignum
    0.13
    Å¡ak
    0.13
    Activations Density 0.005%

    No Known Activations