INDEX

Explanations

titles and roles related to professional positions

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

Ø±ÙĪÛĮ

-0.17

ihan

-0.17

ideo

-0.16

cce

-0.15

oods

-0.15

ä»£

-0.14

ersh

-0.14

ersion

-0.14

dÃ¡l

-0.14

.datab

-0.14

POSITIVE LOGITS

omat

0.17

 role

0.15

ãĥ¼ãĥĨ

0.15

Mot

0.14

çĿ

0.14

 ÑĢÐ¾Ð»ÑĮ

0.14

 Prior

0.14

 Mart

0.13

ãĥ¼ãĤ¿

0.13

Activations Density 0.162%

titles and roles related to professional positions

No Comments

No Known Activations