INDEX

Explanations

phrases indicating potential or suggestions for actions

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

.scalablytyped

-0.16

opsy

-0.16

ÑĢÐµÐ¶

-0.15

ellas

-0.14

achat

-0.14

illard

-0.14

ierung

-0.14

iska

-0.13

AtIndex

-0.13

piler

-0.13

POSITIVE LOGITS

ãĥ¼ãĥĦ

0.17

OTH

0.17

0.15

angu

0.15

Debe

0.15

à¥ģà¤

0.14

ths

0.14

amar

0.14

TextStyle

0.14

Activations Density 0.032%

phrases indicating potential or suggestions for actions

No Comments

No Known Activations