INDEX

Explanations

phrases related to divisions or sections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 drill

-0.15

inds

-0.15

 Investor

-0.15

esen

-0.15

ysi

-0.15

icio

-0.15

 Ø§ÙĦÙĤØ±

-0.15

Ãªu

-0.14

mile

-0.14

eview

-0.14

POSITIVE LOGITS

Ä±t

0.19

ë¦¬ìĸ´

0.15

uche

0.15

ÑĢÑİ

0.15

_Invoke

0.14

APH

0.14

imler

0.14

emsp

0.14

 Architecture

0.14

architecture

0.13

Activations Density 0.274%

phrases related to divisions or sections

No Comments

No Known Activations