INDEX

Explanations

phrases indicating the introduction or arrival of concepts, ideas, or entities into various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

immers

-0.16

ahat

-0.16

raud

-0.15

éĲ

-0.15

 surv

-0.14

hta

-0.14

 ç§

-0.14

zc

-0.14

 downside

-0.14

jn

-0.14

POSITIVE LOGITS

ãĥ¼ãĥĭ

0.15

enta

0.14

ucle

0.14

ynes

0.14

éĥ

0.14

ucher

0.13

_alive

0.13

Cru

0.13

 PhpStorm

0.13

.syntax

0.13

Activations Density 0.137%

phrases indicating the introduction or arrival of concepts, ideas, or entities into various contexts

No Comments

No Known Activations