INDEX

Explanations

the presence of the word "Ka" 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 @ 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

hare

-0.17

ya

-0.17

defgroup

-0.16

uron

-0.16

urr

-0.16

addtogroup

-0.16

utut

-0.15

esteem

-0.15

SETTINGS

-0.15

gent

-0.14

POSITIVE LOGITS

alytics

0.16

ie

0.15

udoku

0.15

agua

0.15

 eens

0.14

 typical

0.14

 indifferent

0.14

-toggler

0.14

ainen

0.14

tub

0.13

Activations Density 0.011%

the presence of the word "Ka" in various contexts

No Comments

No Known Activations