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. Residual Stream
    5. 30-LLAMASCOPE-RES-32K
    6. 8438
    Prev
    Next
    INDEX
    Explanations

    references to mobile phone plans and services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itori
    -0.17
    Č↵
    -0.17
    poon
    -0.16
    ehler
    -0.16
     licensors
    -0.14
    ibar
    -0.14
    onis
    -0.14
    cÃŃm
    -0.14
    LICENSE
    -0.14
     RTE
    -0.14
    POSITIVE LOGITS
     Cricket
    0.29
     carrier
    0.28
     Sprint
    0.27
     AT
    0.26
     wireless
    0.23
     cricket
    0.23
     carriers
    0.23
     Wireless
    0.22
     Device
    0.22
     sprint
    0.22
    Activations Density 0.012%

    No Known Activations