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. 463
    Prev
    Next
    INDEX
    Explanations

    references to ordinal numbers and centuries, particularly in the context of historical periods

    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
    ",__
    -0.18
    icode
    -0.15
    eller
    -0.14
    izzo
    -0.14
    chio
    -0.14
    ÎłÏģο
    -0.14
    æŁľ
    -0.14
    lluminate
    -0.14
    ejs
    -0.13
    dni
    -0.13
    POSITIVE LOGITS
     century
    0.61
    cent
    0.53
     Century
    0.53
    -century
    0.46
    Century
    0.44
    .cent
    0.43
     cent
    0.42
    _cent
    0.41
    CENT
    0.41
     Cent
    0.40
    Activations Density 0.015%

    No Known Activations