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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 18-LLAMASCOPE-RES-32K
    6. 16432
    Prev
    Next
    INDEX
    Explanations

    phrases related to active engagement and involvement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éIJĺ
    -0.16
    ActivityResult
    -0.15
    fold
    -0.15
    plevel
    -0.14
    à¸ģำ
    -0.14
    nga
    -0.14
    Exiting
    -0.14
    eni
    -0.14
    xit
    -0.14
    ãĥĥãĤ¯ãĤ¹
    -0.14
    POSITIVE LOGITS
    -active
    0.32
    /pass
    0.31
    (active
    0.27
    active
    0.25
    -duty
    0.25
    .Active
    0.25
    /react
    0.25
    _inactive
    0.24
     Active
    0.24
     active
    0.23
    Activations Density 0.029%

    No Known Activations