INDEX

Explanations

text related to corporate identity and responsibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

och

-0.18

warts

-0.15

AMA

-0.15

ãĤ¢ãĥ³

-0.14

_proto

-0.14

 Cary

-0.14

 Hooks

-0.14

 pronounced

-0.14

oj

-0.14

ISCO

-0.14

POSITIVE LOGITS

erif

0.16

 Shapiro

0.15

GI

0.14

zej

0.14

 Hubbard

0.14

Ø¹Ø§Ø±

0.14

likle

0.14

 ÐľÐ¾ÑĢ

0.13

age

0.13

oney

0.13

Activations Density 0.233%

text related to corporate identity and responsibilities

No Comments

No Known Activations