INDEX

Explanations

references to transcription-related processes and terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

uppy

-0.17

ä¿Ĥ

-0.16

thed

-0.15

COLUMN

-0.15

 Ange

-0.15

.verbose

-0.14

Isa

-0.14

 column

-0.13

airie

-0.13

ÑĢÐµÐ¹

-0.13

POSITIVE LOGITS

neau

0.21

Äįel

0.18

Î¼Î¼

0.17

ãĥ³ãĥĦ

0.16

.AutoComplete

0.15

ilim

0.15

atron

0.15

aldo

0.15

ãĥ»ãĥ»ãĥ»↵↵

0.14

cao

0.14

Activations Density 0.013%

references to transcription-related processes and terminology

No Comments

No Known Activations