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. 32625
    Prev
    Next
    INDEX
    Explanations

    technical commands and coding syntax

    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
    ukan
    -0.20
    apult
    -0.19
    lion
    -0.18
     Sutton
    -0.16
    301
    -0.15
    sy
    -0.15
    yaw
    -0.15
    æĮģãģ¡
    -0.15
    lite
    -0.15
     Alias
    -0.15
    POSITIVE LOGITS
    rib
    0.15
    elden
    0.15
    hei
    0.15
    osu
    0.15
    618
    0.15
     Cur
    0.14
     Citizenship
    0.14
    oter
    0.14
    uppercase
    0.14
    درÛĮ
    0.14
    Activations Density 0.146%

    No Known Activations