INDEX

Explanations

closing brackets and braces in structured formats like JSON or code

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

ing

-0.32

-0.18

ING

-0.18

itz

-0.16

ufen

-0.15

ĶåĽŀ

-0.15

sak

-0.15

avana

-0.15

lund

-0.15

-0.14

POSITIVE LOGITS

#ab

0.15

#ac

0.15

iÃªu

0.15

ively

0.14

Gle

0.14

gest

0.14

ex

0.14

urs

0.14

ãģ¥

0.13

uchos

0.13

Activations Density 0.180%

closing brackets and braces in structured formats like JSON or code

No Comments

No Known Activations