INDEX

Explanations

the various forms of the word "behavior."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

oks

-0.17

uum

-0.17

pin

-0.17

unnel

-0.16

road

-0.15

eum

-0.15

dob

-0.15

needle

-0.15

xs

-0.15

SSF

-0.14

POSITIVE LOGITS

-Am

0.17

airy

0.17

lsen

0.16

beh

0.16

IOR

0.16

beh

0.16

rens

0.15

 scor

0.15

scient

0.15

utory

0.14

Activations Density 0.033%

the various forms of the word "behavior."

No Comments

No Known Activations