INDEX

Explanations

phrases indicating options or choices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

vla

-0.15

anche

-0.15

sWith

-0.15

adin

-0.15

arel

-0.15

ÙĦÙĤ

-0.14

 nackte

-0.14

erna

-0.14

achuset

-0.14

sci

-0.14

POSITIVE LOGITS

wel

0.20

anged

0.20

theless

0.19

zeit

0.18

phans

0.18

-than

0.17

-sex

0.17

anges

0.15

è®¸

0.15

0.14

Activations Density 0.023%

phrases indicating options or choices

No Comments

No Known Activations