INDEX

Explanations

legal and formal terms related to agreements and responsibilities

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

atel

-0.16

anders

-0.15

ebi

-0.14

dera

-0.14

ga

-0.14

 reductions

-0.14

esh

-0.14

het

-0.14

ooky

-0.14

Ð°ÑĤÐ¸Ð²

-0.14

POSITIVE LOGITS

lant

0.16

ydk

0.15

 Empty

0.15

;element

0.14

REEN

0.14

ksen

0.14

 ë§ī

0.14

Ð¾ÑĢÐ¾Ð½

0.14

kee

0.13

|--------------------------------------------------------------------------↵

0.13

Activations Density 0.412%

legal and formal terms related to agreements and responsibilities

No Comments

No Known Activations