INDEX

Explanations

instances of the word "upset" in various contexts

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

INGLE

-0.16

hyp

-0.14

ingle

-0.14

yps

-0.14

lp

-0.14

argout

-0.14

hood

-0.14

ForResult

-0.14

efined

-0.13

oci

-0.13

POSITIVE LOGITS

NCY

0.15

¼

0.15

ahren

0.14

TERS

0.14

elmet

0.14

ted

0.13

%f

0.13

 Kingdom

0.13

argc

0.13

zano

0.13

Activations Density 0.006%

instances of the word "upset" in various contexts

No Comments

No Known Activations