Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 26084
    Prev
    Next
    INDEX
    Explanations

    terms related to children's apparel and related products

    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
    essler
    -0.15
    -Za
    -0.15
    ague
    -0.15
    aho
    -0.14
    877
    -0.14
    ri
    -0.13
    ervo
    -0.13
    uur
    -0.13
    lein
    -0.13
    iz
    -0.13
    POSITIVE LOGITS
    ippo
    0.16
     including
    0.15
    including
    0.15
     eins
    0.14
    á»įt
    0.14
     various
    0.14
    енÑģ
    0.14
     either
    0.14
    ëŀį
    0.13
    aka
    0.13
    Activations Density 0.206%

    No Known Activations