INDEX

Explanations

elements related to rules, conditions, or requirements

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

istrovstvÃŃ

-0.17

ÅĽcie

-0.15

theless

-0.14

ugins

-0.14

rient

-0.14

ŃĶ

-0.14

enser

-0.14

desired

-0.14

Å

-0.13

.twimg

-0.13

POSITIVE LOGITS

endar

0.15

 Deputy

0.14

zf

0.14

arged

0.14

ToEnd

0.14

qu

0.13

Pg

0.13

ppard

0.13

 Manit

0.13

uset

0.13

Activations Density 0.035%

elements related to rules, conditions, or requirements

No Comments

No Known Activations