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. 29-LLAMASCOPE-RES-32K
    6. 4731
    Prev
    Next
    INDEX
    Explanations

    financial terms related to insurance policies and compensation structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isd
    -0.14
    ICODE
    -0.14
     Sapphire
    -0.13
    uppe
    -0.13
     vests
    -0.12
    ÑĨÑİ
    -0.12
    /Foundation
    -0.12
    stoi
    -0.12
    .EntityFramework
    -0.12
    isco
    -0.12
    POSITIVE LOGITS
     Sum
    1.25
     sum
    1.22
    Sum
    1.17
    sum
    1.16
    -sum
    1.09
     SUM
    1.07
    _sum
    1.02
    SUM
    1.01
     summ
    1.01
    .sum
    0.97
    Activations Density 0.267%

    No Known Activations