INDEX

Explanations

phrases related to being confined or restricted

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

lobber

-0.15

fic

-0.14

 Resist

-0.14

stalk

-0.14

urger

-0.14

|int

-0.14

 Careers

-0.14

wick

-0.13

SI

-0.13

POSITIVE LOGITS

Äįan

0.16

Cube

0.15

oda

0.15

reta

0.14

onto

0.14

athe

0.14

nds

0.14

êµĲ

0.14

 Rash

0.14

usher

0.13

Activations Density 0.039%

phrases related to being confined or restricted

No Comments

No Known Activations