INDEX

Explanations

specific numerical data and related identifiers in texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

achts

-0.21

Ãłn

-0.17

venida

-0.16

 responsible

-0.15

¶Į

-0.15

 kill

-0.14

kill

-0.14

 groupBox

-0.14

↵

-0.14

Kill

-0.14

POSITIVE LOGITS

orz

0.16

*)((

0.14

.dispatch

0.14

_REQUIRE

0.14

ement

0.14

 urlpatterns

0.14

á»Ļc

0.14

iversit

0.13

çł

0.13

iej

0.13

Activations Density 0.003%

specific numerical data and related identifiers in texts

No Comments

No Known Activations