INDEX

Explanations

proper nouns related to notable individuals and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 genders

-0.16

zee

-0.15

oras

-0.15

ê³¼ìłķ

-0.14

gender

-0.14

 Ð³ÑĢÐ¾Ð¼Ð°Ð´

-0.14

éģĬ

-0.14

ifes

-0.14

gross

-0.13

 cris

-0.13

POSITIVE LOGITS

(G

0.19

EDIA

0.17

=G

0.16

(GL

0.16

/G

0.15

erli

0.15

.GL

0.14

Gl

0.14

Ø¬Ø¨

0.14

Activations Density 0.222%

proper nouns related to notable individuals and institutions

No Comments

No Known Activations