INDEX

Explanations

references to ergonomic design and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ccion

-0.17

oria

-0.16

lyph

-0.16

 Snowden

-0.15

Reusable

-0.15

 Boots

-0.14

sian

-0.14

ì»

-0.14

ield

-0.14

odka

-0.14

POSITIVE LOGITS

adians

0.17

ÑģÑĤÐ°

0.16

hole

0.14

Fatal

0.14

è±Ĩ

0.14

avanaugh

0.14

ul

0.13

Ã«

0.13

zo

0.13

Activations Density 0.008%

references to ergonomic design and concepts

No Comments

No Known Activations