INDEX

Explanations

concepts related to abstract ideas and theories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

unami

-0.16

uggy

-0.15

DOG

-0.15

ÅĽÄĩ

-0.15

age

-0.15

houses

-0.14

ager

-0.14

aments

-0.14

isen

-0.14

iesen

-0.14

POSITIVE LOGITS

ively

0.23

ually

0.22

 concepts

0.17

ual

0.17

 Concepts

0.16

strup

0.16

0.15

drv

0.15

ecure

0.15

Activations Density 0.053%

concepts related to abstract ideas and theories

No Comments

No Known Activations