INDEX

Explanations

phrases indicating a near miss or something being just out of reach

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

alse

-0.16

ikal

-0.15

hardt

-0.15

Ð»Ð¸ÑĪ

-0.15

izr

-0.14

Į

-0.14

ASA

-0.14

agine

-0.14

Lik

-0.14

Ø±ÙĪØ´

-0.14

POSITIVE LOGITS

neau

0.19

 above

0.15

abbo

0.14

ghi

0.14

oppable

0.14

anford

0.14

Ð¸Ð¼Ð²

0.14

 HÃ¼s

0.14

yte

0.14

empo

0.14

Activations Density 0.103%

phrases indicating a near miss or something being just out of reach

No Comments

No Known Activations