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. 32718
    Prev
    Next
    INDEX
    Explanations

    references to online content and resources

    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
     http
    -0.90
     www
    -0.84
     https
    -0.82
    http
    -0.80
    https
    -0.73
    www
    -0.72
    (http
    -0.65
    :http
    -0.61
    	http
    -0.56
    .http
    -0.54
    POSITIVE LOGITS
    olla
    0.15
    _FRAMEBUFFER
    0.15
    ium
    0.14
    fts
    0.14
    edia
    0.13
    бом
    0.13
    ManagerInterface
    0.13
    Ńå·ŀ
    0.13
    hab
    0.12
    ÌĨ
    0.12
    Activations Density 0.160%

    No Known Activations