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. 4-LLAMASCOPE-RES-32K
    6. 25099
    Prev
    Next
    INDEX
    Explanations

    mathematical and logical constructs related to group theory and structures

    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
     ãģ¿
    -0.15
    Ïĥί
    -0.14
    autoload
    -0.14
    faction
    -0.14
    trak
    -0.14
    çĸ¾
    -0.14
    ائÙģ
    -0.14
     unarmed
    -0.14
    ****/↵
    -0.13
    ensem
    -0.13
    POSITIVE LOGITS
    empo
    0.17
    eros
    0.15
    \a
    0.14
    ENAME
    0.14
    åĨĮ
    0.14
    bid
    0.14
    uml
    0.14
    .son
    0.13
    icolor
    0.13
    .expr
    0.13
    Activations Density 0.114%

    No Known Activations