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. 1-LLAMASCOPE-RES-32K
    6. 15604
    Prev
    Next
    INDEX
    Explanations

    references to the name "Levine" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     æ¾
    -0.16
    ums
    -0.16
    æ¾
    -0.16
    gue
    -0.15
    .TestTools
    -0.15
    eness
    -0.14
    ç±į
    -0.14
    rian
    -0.14
    ula
    -0.14
    ramer
    -0.14
    POSITIVE LOGITS
    pt
    0.17
     Mut
    0.16
     fus
    0.16
     rem
    0.15
     copy
    0.15
     Fus
    0.15
    zon
    0.15
    Mut
    0.15
    .Unicode
    0.15
    зм
    0.15
    Activations Density 0.004%

    No Known Activations