INDEX

Explanations

expressions of belief or perceptions of truth

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

cta

-0.19

otte

-0.17

ocol

-0.17

ilir

-0.15

ody

-0.14

dana

-0.14

occo

-0.14

å¸Ń

-0.13

bones

-0.13

ban

-0.13

POSITIVE LOGITS

ÃĹ↵↵

0.18

0.17

 hare

0.15

à¸Ļà¸Ķ

0.15

wap

0.15

.cn

0.15

ihat

0.15

hi

0.14

hr

0.14

 cages

0.14

Activations Density 0.008%

expressions of belief or perceptions of truth

No Comments

No Known Activations