INDEX

Explanations

occurrences of the letter 'W'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

innie

-0.16

iki

-0.15

ka

-0.15

indow

-0.15

ighb

-0.14

Ø®

-0.14

antom

-0.14

quota

-0.14

arrow

-0.14

rang

-0.14

POSITIVE LOGITS

ycl

0.17

acon

0.17

ylie

0.16

Va

0.16

&page

0.15

aus

0.15

isco

0.15

amu

0.15

 Trev

0.15

chs

0.14

Activations Density 0.025%

occurrences of the letter 'W'

No Comments

No Known Activations

occurrences of the letter 'W'

No Comments

No Known Activations