INDEX

Explanations

phrases related to leaving or being out of a certain context or situation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

sg

-0.18

akis

-0.17

 Interstate

-0.16

GRE

-0.15

ise

-0.15

GRE

-0.15

éĿ

-0.15

ataire

-0.14

æĸ¹

-0.14

stad

-0.14

POSITIVE LOGITS

 FÃ©

0.17

Ã¼b

0.16

 datum

0.16

rame

0.15

 Bradford

0.14

 Panda

0.14

AXB

0.14

-valu

0.14

_EXPR

0.14

ì¦

0.14

Activations Density 0.033%

phrases related to leaving or being out of a certain context or situation

No Comments

No Known Activations