INDEX

Explanations

phrases indicating physical interactions or connections

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

 complimentary

-0.17

-0.15

 CircularProgress

-0.14

tail

-0.14

ERTICAL

-0.14

ÙĬØ§ÙĨ

-0.14

auty

-0.14

istor

-0.13

POSITIVE LOGITS

yre

0.15

 Ø¹Ø¯

0.15

igue

0.15

emme

0.15

lers

0.15

yg

0.15

iversal

0.15

å¼ı

0.14

ibre

0.14

EE

0.14

Activations Density 0.026%

phrases indicating physical interactions or connections

No Comments

No Known Activations