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. 30783
    Prev
    Next
    INDEX
    Explanations

    references to databases and database-related terminology

    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
    寧
    -0.17
    za
    -0.15
    peria
    -0.15
    teri
    -0.15
    neau
    -0.15
    ynes
    -0.14
    İ·
    -0.14
    ç´ł
    -0.14
    ngen
    -0.14
    uela
    -0.14
    POSITIVE LOGITS
    AndView
    0.16
    emax
    0.15
    jezd
    0.15
     pret
    0.15
    opis
    0.14
    kker
    0.13
    ipi
    0.13
    jamin
    0.13
    SSION
    0.13
    -Compatible
    0.13
    Activations Density 0.028%

    No Known Activations