INDEX

Explanations

references to project phases and their associated numbers

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

-0.17

elle

-0.15

lady

-0.15

OK

-0.15

quiv

-0.14

ÃŃ

-0.14

ham

-0.14

 Giang

-0.14

@dynamic

-0.14

bit

-0.14

POSITIVE LOGITS

/Branch

0.18

onta

0.17

ÙħØ§

0.15

ÄįÃŃ

0.15

Ã¨ge

0.15

onu

0.15

oriously

0.15

ãĥ¼ãĥĨ

0.15

ëĭ

0.15

ÑĢÑĥÐ·

0.14

Activations Density 0.009%

references to project phases and their associated numbers

No Comments

No Known Activations