© 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. 23-LLAMASCOPE-RES-32K
    11. 28029
    Prev
    Next
    INDEX
    Explanations

    terms related to real estate transactions and inspections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uzz
    -0.18
    秣
    -0.18
    rent
    -0.17
    ental
    -0.15
    /archive
    -0.15
    -selector
    -0.14
     vent
    -0.14
     kulak
    -0.14
    enth
    -0.14
     leasing
    -0.14
    POSITIVE LOGITS
     title
    0.43
     Title
    0.38
     esc
    0.37
     Closing
    0.34
    title
    0.34
     closing
    0.33
     TITLE
    0.33
     titles
    0.32
    /title
    0.32
     Esc
    0.30
    Activations Density 0.043%

    No Known Activations