INDEX

Explanations

phrases that emphasize totality or completeness

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

dex

-0.15

ogne

-0.15

etag

-0.15

lassen

-0.14

aded

-0.14

 Equivalent

-0.14

Fog

-0.14

rouch

-0.14

ogn

-0.13

outer

-0.13

POSITIVE LOGITS

ieg

0.17

iferay

0.15

brick

0.15

_hooks

0.15

alah

0.15

chu

0.14

.medium

0.14

ones

0.14

oui

0.14

awi

0.14

Activations Density 0.012%

phrases that emphasize totality or completeness

No Comments

No Known Activations