INDEX

Explanations

specific symbols or characters, likely processing special formatting or encoding in the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

_bullet

-0.14

ikhail

-0.13

izon

-0.13

 diarr

-0.13

hci

-0.12

 Hyundai

-0.12

pNet

-0.12

divider

-0.12

osing

-0.12

Bai

-0.11

POSITIVE LOGITS

 clues

0.28

 puzzle

0.26

 Puzzle

0.26

 puzzles

0.25

 cryptographic

0.25

 crypt

0.24

 puzz

0.23

 cryptography

0.23

 clue

0.21

 cipher

0.21

Activations Density 0.003%

specific symbols or characters, likely processing special formatting or encoding in the text

No Comments

No Known Activations