© 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. 15-LLAMASCOPE-RES-32K
    11. 2593
    Prev
    Next
    INDEX
    Explanations

    expressions of apologies and explanations of delays or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Harding
    -0.17
    rael
    -0.17
    mn
    -0.15
    ifter
    -0.14
     dangerously
    -0.14
    lock
    -0.14
     ë§Ŀ
    -0.14
    .Interop
    -0.13
    CTR
    -0.13
     arm
    -0.13
    POSITIVE LOGITS
     apology
    0.32
     apologies
    0.30
     apolog
    0.30
     apologize
    0.27
     apologized
    0.26
     Ap
    0.26
     apologise
    0.26
     Sorry
    0.23
     sorry
    0.22
    Sorry
    0.22
    Activations Density 0.169%

    No Known Activations