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. 660
    Prev
    Next
    INDEX
    Explanations

    elements related to themes and contextual information in the text

    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
    ness
    -0.63
    nya
    -0.54
    ìĿĦ
    -0.54
    so
    -0.46
    ne
    -0.44
    sh
    -0.43
    name
    -0.43
    ship
    -0.41
    ly
    -0.40
    land
    -0.39
    POSITIVE LOGITS
    ÙĶ
    0.32
    eeee
    0.29
    aux
    0.28
    urope
    0.28
    e
    0.26
    eee
    0.25
    able
    0.25
    iro
    0.23
    âĢĮاÛĮ
    0.23
    au
    0.22
    Activations Density 2.386%

    No Known Activations