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. 23-LLAMASCOPE-RES-32K
    6. 11699
    Prev
    Next
    INDEX
    Explanations

    concepts related to complex situations and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reib
    -0.15
     breed
    -0.13
     Voting
    -0.13
    unce
    -0.13
     spou
    -0.13
    itten
    -0.13
     scor
    -0.13
    ingles
    -0.12
     alter
    -0.12
    ãģĵãģ¡ãĤī
    -0.12
    POSITIVE LOGITS
     visit
    0.38
     encounter
    0.30
     transaction
    0.29
    visit
    0.28
     session
    0.28
     trip
    0.27
     experiment
    0.25
     sale
    0.24
     purchase
    0.24
     appointment
    0.24
    Activations Density 0.894%

    No Known Activations