INDEX

Explanations

references to the concept of "back."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

argout

-0.18

avax

-0.17

 backgrounds

-0.16

background

-0.15

SSI

-0.14

gÃ¼n

-0.14

eka

-0.14

quence

-0.14

ilda

-0.14

apse

-0.14

POSITIVE LOGITS

wards

0.33

slash

0.31

ronym

0.25

slashes

0.24

side

0.22

ward

0.22

door

0.21

WARDS

0.20

lashes

0.19

ruptcy

0.19

Activations Density 0.104%

references to the concept of "back."

No Comments

No Known Activations