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. MLP
    5. 22-LLAMASCOPE-MLP-32K
    6. 32714
    Prev
    Next
    INDEX
    Explanations

    concerns related to transparency and accountability in educational institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama3_1-8B-Base-LXM-8x/Llama3_1-8B-Base-L22M-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_mlp_out
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ziej
    -0.16
    .dequeue
    -0.15
    brook
    -0.15
    lili
    -0.14
    OLON
    -0.14
     Ñħви
    -0.14
     Trials
    -0.14
     hữu
    -0.14
    pkg
    -0.14
    poÄį
    -0.13
    POSITIVE LOGITS
     school
    0.21
     schooling
    0.19
     schools
    0.18
     teacher
    0.18
     SCHOOL
    0.18
     School
    0.17
     teachers
    0.17
     teaching
    0.17
    åŃ¸æł¡
    0.16
     instructors
    0.16
    Activations Density 0.640%

    No Known Activations