INDEX

Explanations

instances of the word "over" 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 @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ic

-0.20

qui

-0.17

ickle

-0.17

Oc

-0.16

oci

-0.16

shan

-0.15

rox

-0.15

Ð¼ÐµÐ»ÑĮ

-0.15

aday

-0.15

ikit

-0.15

POSITIVE LOGITS

tones

0.21

alls

0.18

drive

0.17

eview

0.16

nite

0.16

ãĤ¤ãĥĦ

0.15

 dram

0.15

kill

0.15

brero

0.15

AGMENT

0.15

Activations Density 0.052%

instances of the word "over" in various contexts

No Comments

No Known Activations