© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 28-LLAMASCOPE-RES-32K
    11. 19728
    Prev
    Next
    INDEX
    Explanations

    terms related to comparisons and distinctions between items or concepts

    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
    igel
    -0.14
    eyim
    -0.14
    InputBorder
    -0.13
    ãģĻãģĻ
    -0.13
     Certain
    -0.13
     besonders
    -0.13
    žil
    -0.13
     Relevant
    -0.13
    iverse
    -0.12
    Ïĩο
    -0.12
    POSITIVE LOGITS
     traditional
    0.79
     conventional
    0.77
     regular
    0.76
     normal
    0.76
     usual
    0.69
    traditional
    0.65
     ordinary
    0.64
     standard
    0.63
    normal
    0.61
    regular
    0.61
    Activations Density 0.947%

    No Known Activations