INDEX

Explanations

phrases related to packing and organization

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

eb

-0.16

ovah

-0.15

 onto

-0.14

auss

-0.14

itten

-0.14

aint

-0.14

stand

-0.13

wide

-0.13

UCH

-0.13

 strncmp

-0.13

POSITIVE LOGITS

 tucked

0.25

 secure

0.21

 button

0.20

 hiding

0.19

-button

0.19

 nest

0.19

 bund

0.19

 Button

0.19

 hides

0.18

Nested

0.18

Activations Density 0.121%

phrases related to packing and organization

No Comments

No Known Activations