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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 28-LLAMASCOPE-RES-32K
    11. 31099
    Prev
    Next
    INDEX
    Explanations

    properties and attributes related to user interface components in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '[
    -0.23
     '..
    -0.18
     '#
    -0.17
     '{@
    -0.17
    ['__
    -0.17
     '$
    -0.15
    '[
    -0.15
    -quote
    -0.15
    imestone
    -0.15
    sdale
    -0.15
    POSITIVE LOGITS
    ="
    0.21
     "
    0.21
    ("
    0.18
    álo
    0.16
    Mvc
    0.15
    ["
    0.15
     Gor
    0.15
    ¿
    0.15
     ="
    0.15
    İ
    0.14
    Activations Density 0.151%

    No Known Activations