INDEX

Explanations

references related to education and academic achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

æµİ

-0.12

ÏģÎ±Î²

-0.11

Ã©ru

-0.11

ÄĽli

-0.10

á»ĭch

-0.10

getSingleton

-0.10

ÐµÐ´Ð¶

-0.10

Ã¢u

-0.10

niÅ¾

-0.10

OMEM

-0.10

POSITIVE LOGITS

1.00

-Y

0.89

0.86

/Y

0.84

_Y

0.84

,Y

0.81

(Y

0.81

0.78

.Y

0.77

[Y

0.74

Activations Density 1.044%

references related to education and academic achievements

No Comments

No Known Activations