INDEX

Explanations

mentions of tension or conflict 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 @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

aring

-0.17

ç«¥

-0.15

REE

-0.15

EDA

-0.15

iaux

-0.14

uting

-0.14

anes

-0.14

zeÅĪ

-0.14

ared

-0.14

ersistence

-0.14

POSITIVE LOGITS

_AF

0.17

burg

0.16

er

0.15

èľľ

0.15

mere

0.14

ÌĤ

0.14

tar

0.14

 prob

0.14

stakes

0.14

grams

0.14

Activations Density 0.009%

mentions of tension or conflict in various contexts

No Comments

No Known Activations