© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 23-LLAMASCOPE-RES-32K
    6. 20779
    Prev
    Next
    INDEX
    Explanations

    phrases indicating moral judgment or evaluation

    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
     since
    -0.19
    asm
    -0.18
    since
    -0.18
     pues
    -0.17
     considering
    -0.17
     seit
    -0.16
    awn
    -0.15
     Since
    -0.15
    unless
    -0.15
    Since
    -0.14
    POSITIVE LOGITS
     because
    0.48
     Because
    0.42
     porque
    0.41
    because
    0.40
    Because
    0.40
     поÑĤомÑĥ
    0.35
    åĽłä¸º
    0.34
    ecause
    0.33
     omdat
    0.33
     parce
    0.32
    Activations Density 0.172%

    No Known Activations