INDEX

Explanations

occurrences of specific formatting or notation styles in scientific writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 Text

-0.18

 text

-0.17

_text

-0.16

olen

-0.15

Text

-0.15

-txt

-0.15

TextEdit

-0.15

.Text

-0.15

-text

-0.15

igung

-0.15

POSITIVE LOGITS

bf

0.30

tt

0.27

it

0.24

numero

0.22

sl

0.22

sf

0.22

sc

0.20

color

0.20

BF

0.18

normal

0.18

Activations Density 0.015%

occurrences of specific formatting or notation styles in scientific writing

No Comments

No Known Activations