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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 18-LLAMASCOPE-RES-32K
    11. 995
    Prev
    Next
    INDEX
    Explanations

    references to teaching and education-related scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     toll
    -0.17
     hires
    -0.14
    arken
    -0.14
     rowCount
    -0.14
    ultiply
    -0.14
    emi
    -0.14
    uf
    -0.13
     precipitation
    -0.13
    opers
    -0.13
     nackte
    -0.13
    POSITIVE LOGITS
     assignment
    0.50
     assigned
    0.48
    assigned
    0.46
     assignments
    0.45
     Assigned
    0.44
    assignment
    0.43
    Assignment
    0.43
     Assignment
    0.43
     Assign
    0.42
    Assigned
    0.42
    Activations Density 0.255%

    No Known Activations