INDEX

Explanations

phrases related to living conditions or environments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

strand

-0.17

urovision

-0.17

Ð°Ð½Ð³

-0.16

stead

-0.16

anko

-0.15

ÑĩÐµÑģÐºÐ¸

-0.14

onu

-0.14

ÙģØ§ÙĤ

-0.14

alat

-0.13

getc

-0.13

POSITIVE LOGITS

 relative

0.26

relative

0.23

-relative

0.22

 Relative

0.20

 conditions

0.18

 surroundings

0.17

 unfamiliar

0.17

 environments

0.17

 uncertainty

0.16

Relative

0.16

Activations Density 0.248%

phrases related to living conditions or environments

No Comments

No Known Activations