INDEX

Explanations

information about authors and their contributions, particularly in the context of media and academic releases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

Ã¡tek

-0.17

ECTOR

-0.15

toi

-0.14

owo

-0.14

_Syntax

-0.14

Ð²Ð°Ð¹

-0.14

ERGY

-0.14

:maj

-0.14

/*č↵

-0.14

olor

-0.14

POSITIVE LOGITS

 stories

0.18

 reporting

0.17

 local

0.16

 cubes

0.16

 chronic

0.16

 news

0.15

aje

0.15

Fel

0.15

 Reporting

0.15

Activations Density 0.204%

information about authors and their contributions, particularly in the context of media and academic releases

No Comments

No Known Activations