INDEX

Explanations

phrases indicating anticipation or expectation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

adel

-0.16

ery

-0.15

ahr

-0.15

alous

-0.14

essler

-0.14

 Hund

-0.14

upal

-0.14

istros

-0.14

.GroupLayout

-0.14

esa

-0.13

POSITIVE LOGITS

orate

0.27

ably

0.20

antly

0.20

oe

0.18

ose

0.16

iams

0.16

ingly

0.15

STS

0.15

entially

0.15

ilog

0.15

Activations Density 0.045%

phrases indicating anticipation or expectation

No Comments

No Known Activations