INDEX

Explanations

occurrences of the word "To" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

au

-0.17

ford

-0.17

ro

-0.17

naire

-0.17

Ø³ÙĪ

-0.16

udu

-0.16

ÑĢÐ¾Ð´

-0.16

usive

-0.16

bou

-0.15

POSITIVE LOGITS

oldown

0.21

hiba

0.21

ledo

0.21

 whom

0.20

onces

0.20

è¾¾

0.19

aster

0.19

alet

0.18

xic

0.18

ilers

0.17

Activations Density 0.085%

occurrences of the word "To" in various contexts

No Comments

No Known Activations