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. 18-LLAMASCOPE-RES-32K
    6. 24571
    Prev
    Next
    INDEX
    Explanations

    dates and numerical references, particularly related to events or time periods

    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
    onomic
    -0.17
    eenth
    -0.17
    nut
    -0.17
    een
    -0.16
    รร
    -0.16
    iterations
    -0.15
    steen
    -0.15
    дина
    -0.15
    fer
    -0.15
    illum
    -0.14
    POSITIVE LOGITS
    tere
    0.19
    inis
    0.16
    ials
    0.16
    ÙĦØ©
    0.15
    chg
    0.15
    allback
    0.15
    mer
    0.14
    UNCH
    0.14
    sole
    0.14
    央
    0.14
    Activations Density 0.128%

    No Known Activations