INDEX

Explanations

phrases related to political processes and negotiations

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

leine

-0.17

.opens

-0.15

CharCode

-0.14

urrent

-0.14

 ìı

-0.14

uche

-0.14

ÅĻÃŃd

-0.14

insi

-0.14

POSITIVE LOGITS

 solution

0.24

 halt

0.22

 repeat

0.21

 possible

0.21

 scenario

0.20

 future

0.20

solution

0.19

 return

0.19

 eventual

0.19

 further

0.18

Activations Density 0.272%

phrases related to political processes and negotiations

No Comments

No Known Activations