INDEX

Explanations

repeated mentions or emphasis of the term "co" or variations thereof

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

é¾

-0.18

ktop

-0.16

amage

-0.15

ÐµÑĢÑĪ

-0.15

ephy

-0.14

cloak

-0.14

Ð»Ð¸ÑĪÐºÐ¾Ð¼

-0.14

Yam

-0.14

AGMA

-0.14

 BASIC

-0.14

POSITIVE LOGITS

anut

0.17

gett

0.15

imat

0.15

thon

0.15

eland

0.15

Ð¾ÑģÑĢÐµÐ´

0.15

buz

0.14

xhr

0.14

croft

0.14

ï¼

0.14

Activations Density 0.034%

repeated mentions or emphasis of the term "co" or variations thereof

No Comments

No Known Activations