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. 25-LLAMASCOPE-RES-32K
    6. 10772
    Prev
    Next
    INDEX
    Explanations

    phrases related to competitive events and their logistics

    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
    ubo
    -0.17
    orsch
    -0.16
    ilet
    -0.16
    jeta
    -0.15
    abis
    -0.14
    &view
    -0.14
    .snapshot
    -0.14
    ãĥ¼ãĥľ
    -0.14
    410
    -0.14
    617
    -0.14
    POSITIVE LOGITS
     back
    0.82
    back
    0.64
     Back
    0.60
    -back
    0.60
    Back
    0.60
    _back
    0.57
     BACK
    0.56
     consecutive
    0.55
    .back
    0.50
     successive
    0.47
    Activations Density 0.080%

    No Known Activations