INDEX

Explanations

phrases associated with case studies and examples of practice

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

 Morrow

-0.16

ered

-0.15

 ÙģØ§Ø±

-0.14

erca

-0.14

 competitive

-0.14

ersed

-0.14

å½Ĵ

-0.14

elta

-0.14

 Lager

-0.14

fty

-0.14

POSITIVE LOGITS

case

0.18

0.17

 exemple

0.17

 Partial

0.16

åĽ

0.16

cases

0.15

éŁ¿

0.15

 case

0.15

Activations Density 0.316%

phrases associated with case studies and examples of practice

No Comments

No Known Activations