INDEX

Explanations

references to challenges and difficulties faced in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

seg

-0.16

-thirds

-0.16

se

-0.15

ÃľM

-0.15

folk

-0.15

çļ

-0.15

ãģ¹ãģį

-0.15

ogle

-0.15

adlo

-0.15

oldown

-0.14

POSITIVE LOGITS

ingly

0.19

0.17

íĦ

0.17

0.16

iar

0.15

horn

0.15

rd

0.14

hari

0.14

TEGER

0.14

Activations Density 0.034%

references to challenges and difficulties faced in various contexts

No Comments

No Known Activations