INDEX

Explanations

timestamps

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

th

-0.15

adol

-0.15

aber

-0.15

pike

-0.14

Bro

-0.13

utton

-0.13

thro

-0.13

 Cook

-0.13

pi

-0.13

paired

-0.13

POSITIVE LOGITS

mee

0.17

áº¯c

0.16

ynet

0.15

Ø¬Ø§Øª

0.15

 sá»©

0.14

lettes

0.14

 ìĤ

0.14

LETTE

0.14

tee

0.14

stants

0.14

Activations Density 0.015%

timestamps

No Comments

No Known Activations