INDEX

Explanations

phrases related to significant locations and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

istrat

-0.15

éĽĦ

-0.14

ertia

-0.14

 Lionel

-0.14

ierz

-0.14

issen

-0.14

','=',$

-0.14

ÐµÐ½Ñı

-0.14

:".$

-0.14

cala

-0.14

POSITIVE LOGITS

ranking

0.16

.tf

0.15

Ð¾Ð»Ð¾Ð¼

0.14

tero

0.14

.locals

0.14

»

0.14

åĭĴ

0.14

ÑĥÐ¹

0.14

Î

0.13

Ð²ÐµÐ´

0.13

Activations Density 0.006%

phrases related to significant locations and their implications

No Comments

No Known Activations