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
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 25952
    Prev
    Next
    INDEX
    Explanations

    notations or symbols that signify actions or categories in structured data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erna
    -0.18
    ses
    -0.17
    اÙĨÙĩ
    -0.16
    ëĿ½
    -0.16
    ationship
    -0.15
    ihar
    -0.15
    ighb
    -0.15
    ÏĦον
    -0.15
    erm
    -0.15
    entials
    -0.15
    POSITIVE LOGITS
    kwargs
    0.22
    *>
    0.20
    *(
    0.20
    */
    0.19
    ³³³³³
    0.19
    *)
    0.18
    ³³³³³³³
    0.17
    ³³³³³³
    0.17
    ³³³³³³³³
    0.17
    ician
    0.17
    Activations Density 0.029%

    No Known Activations