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. 4-LLAMASCOPE-RES-32K
    6. 31035
    Prev
    Next
    INDEX
    Explanations

    mentions of "body of work" or references to collections of works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abyrin
    -0.20
    ̣
    -0.16
    azio
    -0.15
    .elementAt
    -0.15
    itz
    -0.15
    uby
    -0.14
    اÙĦÙĩ
    -0.14
     cref
    -0.14
    /filepath
    -0.14
    eras
    -0.14
    POSITIVE LOGITS
    بس
    0.14
    ëĨĵ
    0.14
    .epam
    0.14
     Larger
    0.14
    finger
    0.13
    vise
    0.13
     developing
    0.13
    quake
    0.13
    Body
    0.13
     Kitt
    0.13
    Activations Density 0.011%

    No Known Activations