INDEX

Explanations

names of people and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

dyn

-0.17

svp

-0.16

reon

-0.16

IDAD

-0.16

unner

-0.16

 vict

-0.15

anax

-0.15

atk

-0.15

OnError

-0.15

irse

-0.15

POSITIVE LOGITS

Ã²

0.28

Ã¬

0.26

azz

0.23

acc

0.21

Ã²n

0.20

Ã¨

0.20

aggio

0.20

ini

0.20

igli

0.20

izz

0.19

Activations Density 0.089%

names of people and places

No Comments

No Known Activations