INDEX

Explanations

references to academic and professional qualifications and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

efs

-0.16

roof

-0.15

ricks

-0.15

 DÃ¼n

-0.15

 bruk

-0.14

 ØµÙĪØ±

-0.14

heels

-0.14

ushman

-0.14

.MixedReality

-0.14

 Partners

-0.14

POSITIVE LOGITS

 personals

0.16

YM

0.16

Î¼Îµ

0.15

amine

0.15

ofil

0.14

 Rotary

0.14

PG

0.13

Ĺ

0.13

Ð°Ð»ÑĮ

0.13

 tuned

0.13

Activations Density 0.058%

references to academic and professional qualifications and experiences

No Comments

No Known Activations