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

    Neuronpedia

    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. 6850
    Prev
    Next
    INDEX
    Explanations

    phrases related to narratives, user interface elements, and user inputs in a structured format

    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
    !!!!↵↵
    -0.17
    .scalablytyped
    -0.16
    ":č↵
    -0.15
    )prepare
    -0.13
    ¡´
    -0.13
    ']:
    -0.13
    %";↵
    -0.13
    สà¸ģ
    -0.13
    hill
    -0.13
    exter
    -0.13
    POSITIVE LOGITS
    Lorem
    0.16
    marvin
    0.16
    \n
    0.14
    &nbsp
    0.14
     ipsum
    0.14
    £i
    0.14
    letcher
    0.13
    (?:
    0.13
    \xa
    0.13
    ाà¤ĸ
    0.13
    Activations Density 0.191%

    No Known Activations