© 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. 24-LLAMASCOPE-RES-32K
    11. 12683
    Prev
    Next
    INDEX
    Explanations

    elements of code related to data structures and their properties, particularly focusing on array or list lengths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uner
    -0.16
    anine
    -0.15
    tridge
    -0.15
    á»ı
    -0.14
    isel
    -0.14
    ibu
    -0.14
    ankan
    -0.14
    èĵ
    -0.13
    ody
    -0.13
    ynet
    -0.13
    POSITIVE LOGITS
    -
    0.52
    Minus
    0.24
    _minus
    0.23
    -'
    0.23
    minus
    0.21
    -âĢIJ
    0.21
    âĪĴ
    0.20
    {-
    0.20
     minus
    0.20
    _MINUS
    0.18
    Activations Density 0.202%

    No Known Activations