INDEX

Explanations

phrases indicating the presence of tables or data structures in technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

illac

-0.18

ano

-0.16

ared

-0.15

itaire

-0.14

arkan

-0.14

rud

-0.14

arts

-0.13

 Acres

-0.13

icare

-0.13

POSITIVE LOGITS

 edip

0.16

.opendaylight

0.15

Sez

0.15

ervers

0.14

ATUS

0.14

IMITER

0.14

buz

0.14

ToProps

0.13

Ð¾Ð»ÑĮÐ·Ð¾Ð²Ð°ÑĤ

0.13

compact

0.13

Activations Density 0.063%

phrases indicating the presence of tables or data structures in technical contexts

No Comments

No Known Activations