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. 29636
    Prev
    Next
    INDEX
    Explanations

    mentions of technical issues or features related to software systems

    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
    asha
    -0.17
    .Library
    -0.16
    bow
    -0.15
     Pinterest
    -0.14
    Ñħи
    -0.14
    gif
    -0.14
    itto
    -0.14
     tear
    -0.14
    Pinterest
    -0.14
     bow
    -0.14
    POSITIVE LOGITS
     CVS
    0.28
     cvs
    0.26
     Bug
    0.24
    .sourceforge
    0.23
     bug
    0.22
     trunk
    0.21
     mailing
    0.21
    -devel
    0.21
     Savannah
    0.21
    CV
    0.20
    Activations Density 0.108%

    No Known Activations