INDEX

Explanations

phrases related to tasks or efforts performed

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

 last

-0.15

LAST

-0.15

 Edgar

-0.15

 minor

-0.14

 mist

-0.14

mitt

-0.14

EF

-0.14

 First

-0.14

 everything

-0.14

 Minor

-0.14

POSITIVE LOGITS

 Casc

0.19

åĿĬ

0.17

ÑıÑĩ

0.16

itness

0.16

.Debugger

0.15

muz

0.15

Wunused

0.15

Ã¡Å¾

0.15

RuntimeObject

0.15

flater

0.15

Activations Density 0.118%

phrases related to tasks or efforts performed

No Comments

No Known Activations