INDEX

Explanations

technical terms related to programming and date formatting

oai_token-act-pair · gpt-4o-mini Triggered 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

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Hancock

-0.15

hal

-0.15

-0.14

raft

-0.14

sil

-0.14

 Dirk

-0.14

 fond

-0.14

 rede

-0.14

POSITIVE LOGITS

 formats

0.38

 format

0.38

 Format

0.37

format

0.35

-format

0.34

 FORMAT

0.33

.format

0.32

 Formats

0.32

Format

0.32

 formato

0.32

Activations Density 0.064%

technical terms related to programming and date formatting

No Comments

No Known Activations