INDEX

Explanations

intensifiers or modifiers emphasizing the degree of something, particularly the word "really."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

Ã¤d

-0.16

rav

-0.16

rous

-0.15

chwitz

-0.15

 mere

-0.15

ese

-0.15

raz

-0.15

ner

-0.14

eldorf

-0.14

ady

-0.14

POSITIVE LOGITS

ignment

0.21

ationship

0.20

 estate

0.18

yy

0.17

bigint

0.17

igned

0.16

uger

0.16

-world

0.16

yyy

0.16

uste

0.16

Activations Density 0.053%

intensifiers or modifiers emphasizing the degree of something, particularly the word "really."

No Comments

No Known Activations