© 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. 16-LLAMASCOPE-RES-32K
    11. 21283
    Prev
    Next
    INDEX
    Explanations

    phrases about reflection and hindsight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enti
    -0.18
    NEXT
    -0.15
    çºĮ
    -0.15
    ÑĨин
    -0.15
    zet
    -0.15
    abay
    -0.14
    ìĨĶ
    -0.13
    brief
    -0.13
    edium
    -0.13
    PointerType
    -0.13
    POSITIVE LOGITS
     retro
    0.43
     retrospect
    0.39
     retrospective
    0.38
     hindsight
    0.38
     later
    0.38
     Retro
    0.32
     post
    0.32
     after
    0.31
     AFTER
    0.30
     retrofit
    0.29
    Activations Density 0.273%

    No Known Activations