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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 28-LLAMASCOPE-RES-32K
    6. 371
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and entities related to the National Broadband Network (NBN) and its impact on Australian businesses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izmet
    -0.15
    ìĿ´íĦ°
    -0.14
    nick
    -0.14
    (nav
    -0.13
     navbar
    -0.13
    ichni
    -0.13
    nez
    -0.12
    newInstance
    -0.12
    naz
    -0.12
     newInstance
    -0.12
    POSITIVE LOGITS
     N
    1.41
    N
    1.05
    ÂłN
    0.86
    .N
    0.76
    =N
    0.75
    	N
    0.72
    *N
    0.68
     ÐĿ
    0.68
    _N
    0.66
    :N
    0.66
    Activations Density 0.853%

    No Known Activations