INDEX

Explanations

instances of the word "while."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

aid

-0.18

Aid

-0.17

-0.15

 lone

-0.14

anity

-0.14

anta

-0.14

 Trafford

-0.14

çļĦåľ°

-0.14

soft

-0.14

 Ð¿ÑĢÐ¸Ð´

-0.13

POSITIVE LOGITS

inspace

0.19

ritz

0.17

eniz

0.17

quete

0.16

stery

0.16

bove

0.16

ureau

0.15

iminal

0.15

usercontent

0.15

incr

0.15

Activations Density 0.053%

instances of the word "while."

No Comments

No Known Activations