INDEX

Explanations

mentions or references to the letter 'G'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

áº¡p

-0.18

apid

-0.16

ARIANT

-0.15

PPER

-0.15

latable

-0.14

æĮĩå¯¼

-0.14

ADDE

-0.14

Ã¨o

-0.14

ishment

-0.14

POSITIVE LOGITS

iron

0.30

onz

0.26

arc

0.23

ij

0.23

avir

0.22

IRON

0.21

erman

0.21

erm

0.21

elsen

0.21

uti

0.20

Activations Density 0.022%

mentions or references to the letter 'G'

No Comments

No Known Activations