INDEX

Explanations

acronyms and abbreviations related to systems and organizations

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

ldr

-0.17

fon

-0.15

aise

-0.15

ayÄ±n

-0.14

 vá»¥

-0.14

dro

-0.14

 jobs

-0.14

 flex

-0.14

 motiv

-0.14

alto

-0.14

POSITIVE LOGITS

Ð±ÑĢÐ°

0.17

ennie

0.16

Enumerator

0.16

uide

0.15

reeNode

0.14

 Approval

0.14

aring

0.14

://%

0.14

alue

0.14

Ú¯ÙĪ

0.14

Activations Density 0.094%

acronyms and abbreviations related to systems and organizations

No Comments

No Known Activations