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

    Neuronpedia

    APICircuit 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. 9-LLAMASCOPE-RES-32K
    6. 15930
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial restrictions and conditions for eligibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iture
    -0.15
    SITE
    -0.15
    itable
    -0.14
    strup
    -0.14
    رÙĪØ²
    -0.14
    μί
    -0.14
     Pill
    -0.14
    allis
    -0.14
    обÑĢаз
    -0.14
    лоÑĤ
    -0.14
    POSITIVE LOGITS
    VIC
    0.18
     taped
    0.16
    awy
    0.15
     lean
    0.14
     already
    0.14
    dcc
    0.14
    already
    0.14
    ìŰ
    0.14
    .hp
    0.14
    agu
    0.13
    Activations Density 0.268%

    No Known Activations