INDEX

Explanations

statements regarding the existence or quality of various topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

æĸ¹

-0.14

REFERRED

-0.13

okable

-0.13

REDIT

-0.13

asmus

-0.13

SupportedContent

-0.12

oure

-0.12

Î»Î¿Î½

-0.12

orne

-0.12

OMET

-0.12

POSITIVE LOGITS

 brief

0.23

 lengthy

0.23

 titled

0.22

 pepper

0.21

 longer

0.21

 geared

0.21

 oriented

0.20

cou

0.20

 dated

0.20

 word

0.20

Activations Density 0.194%

statements regarding the existence or quality of various topics

No Comments

No Known Activations