INDEX

Explanations

the word "that" and its variations including its usage in reported speech or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

vro

-0.15

Rif

-0.15

berger

-0.15

/Library

-0.15

uhl

-0.14

 Alive

-0.14

INCLUDE

-0.14

eyer

-0.14

)||(

-0.13

POSITIVE LOGITS

ÑĢÑı

0.17

ÐºÐ°Ð·

0.15

ablish

0.14

psilon

0.14

eworld

0.14

Ton

0.14

raft

0.13

à¹Ģà¸Ńà¸ĩ

0.13

 ↵↵

0.13

Î²Îµ

0.13

Activations Density 0.290%

the word "that" and its variations including its usage in reported speech or statements

No Comments

No Known Activations