INDEX

Explanations

dates mentioned in the text

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

antee

-0.15

elsing

-0.14

arta

-0.14

ogle

-0.14

htub

-0.14

ertas

-0.13

ErrMsg

-0.13

Î¼Î¯

-0.13

addtogroup

-0.13

chte

-0.13

POSITIVE LOGITS

UST

0.16

edd

0.15

ait

0.15

iku

0.15

urons

0.14

redo

0.14

ust

0.14

adol

0.13

orado

0.13

-git

0.13

Activations Density 0.049%

dates mentioned in the text

No Comments

No Known Activations