INDEX

Explanations

search-related terms and phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

umble

-0.18

olon

-0.15

à¸±à¸Ļà¸ĺ

-0.14

ÃĬ

-0.14

rary

-0.14

usta

-0.14

BOR

-0.14

maz

-0.14

Rim

-0.13

POSITIVE LOGITS

erse

0.21

lea

0.16

.Compiler

0.15

éģº

0.15

 vess

0.14

 Glas

0.14

 baptized

0.13

OLS

0.13

ÅĻit

0.13

ÑģÐ¾ÑĤ

0.13

Activations Density 0.015%

search-related terms and phrases

No Comments

No Known Activations