Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 23874
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to user account management in a web application

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    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
     equals
    -0.16
    ĥ
    -0.15
    ìŀĦ
    -0.15
    ause
    -0.14
    imbus
    -0.14
    "go
    -0.14
    odon
    -0.13
    ritis
    -0.13
     equal
    -0.13
    POSITIVE LOGITS
    olan
    0.18
    abela
    0.17
    lander
    0.16
    ,↵
    0.16
    ìĿ´ê³ł
    0.14
    лÑıв
    0.14
    lä
    0.14
     addCriterion
    0.14
    æ´¥
    0.14
    OrNil
    0.14
    Activations Density 0.111%

    No Known Activations