INDEX

Explanations

instances of confrontation or arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

cx

-0.15

infeld

-0.14

“

-0.14

ensch

-0.14

"$

-0.14

 “[

-0.14

isay

-0.13

ertz

-0.13

Fol

-0.13

 stere

-0.13

POSITIVE LOGITS

0.18

alian

0.16

your

0.16

.""

0.15

uh

0.14

 yourselves

0.14

MOTE

0.14

 your

0.14

 yourself

0.14

 obsess

0.13

Activations Density 1.791%

instances of confrontation or arguments

No Comments

No Known Activations