INDEX

Explanations

phrases expressing the potential benefits or positive aspects of a situation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

aman

-0.14

ë¬¸ìĿĦ

-0.14

 Mitar

-0.14

bra

-0.14

oz

-0.13

Å¯m

-0.13

Î¸ÎµÎ½

-0.13

vang

-0.13

ht

-0.13

POSITIVE LOGITS

ondon

0.17

Ã±a

0.16

AGER

0.15

ITTER

0.15

á»Ļi

0.15

 Gross

0.14

[href

0.14

agger

0.14

ought

0.14

.setDefault

0.14

Activations Density 0.276%

phrases expressing the potential benefits or positive aspects of a situation

No Comments

No Known Activations