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. 24-LLAMASCOPE-RES-32K
    6. 5784
    Prev
    Next
    INDEX
    Explanations

    characteristics and descriptions of glass materials and their uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Credits
    -0.15
    anga
    -0.14
    aland
    -0.14
     Alban
    -0.14
    gan
    -0.14
    iem
    -0.14
    tir
    -0.14
    tridge
    -0.13
    wal
    -0.13
     civ
    -0.13
    POSITIVE LOGITS
     glass
    0.76
     Glass
    0.69
    Glass
    0.66
    glass
    0.64
    çİ»çĴĥ
    0.55
     glasses
    0.49
     ÑģÑĤек
    0.45
     Glas
    0.39
     Glasses
    0.39
     kÃŃnh
    0.36
    Activations Density 0.138%

    No Known Activations