© 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. 25-LLAMASCOPE-RES-32K
    11. 18438
    Prev
    Next
    INDEX
    Explanations

    elements related to user interaction and active items in a UI context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pearce
    -0.17
    uce
    -0.16
     Elliott
    -0.16
    uga
    -0.15
    onec
    -0.14
    jah
    -0.14
    otle
    -0.14
    468
    -0.14
    cntl
    -0.13
    noc
    -0.13
    POSITIVE LOGITS
     item
    0.91
    item
    0.80
     Item
    0.76
    -item
    0.71
    _item
    0.71
    Item
    0.69
     items
    0.69
    .item
    0.65
    (item
    0.63
     ITEM
    0.63
    Activations Density 0.077%

    No Known Activations