INDEX

Explanations

references to images and related metadata

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

.inline

-0.15

atcher

-0.14

ÑĥÐ½Ðº

-0.13

éĻµ

-0.13

inne

-0.13

Assignable

-0.13

 Ð·Ð°ÑģÑĤÑĥÐ¿

-0.13

PushButton

-0.13

(fun

-0.13

Ð¾ÑģÑĤÑĸ

-0.13

POSITIVE LOGITS

 Format

0.22

 Resolution

0.21

 Source

0.20

Format

0.18

 Dimension

0.17

ÏģÏīÎ½

0.17

Resolution

0.17

 source

0.17

 format

0.17

 Detail

0.16

Activations Density 0.003%

references to images and related metadata

No Comments

No Known Activations