INDEX

Explanations

numerical values associated with measurements and capacities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

OSE

-0.15

hoa

-0.15

-0.14

ahu

-0.14

peri

-0.14

.Generated

-0.14

irq

-0.13

ç»ĩ

-0.13

omitempty

-0.13

phinx

-0.13

POSITIVE LOGITS

andler

0.17

amba

0.15

norm

0.15

ikler

0.14

ocz

0.14

.opend

0.14

oit

0.14

esty

0.14

 both

0.14

 Bryan

0.14

Activations Density 0.502%

numerical values associated with measurements and capacities

No Comments

No Known Activations