INDEX

Explanations

references to roles, positions, and career transitions in various professional contexts

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

eca

-0.17

ext

-0.15

eking

-0.15

li

-0.14

angu

-0.14

idia

-0.14

Ext

-0.14

ujÄħ

-0.13

POSITIVE LOGITS

ugins

0.17

uden

0.16

ssize

0.15

oksen

0.14

ayet

0.14

loub

0.14

/WebAPI

0.14

woke

0.14

Ð¿ÑĢÐ¸ÐºÐ»Ð°Ð´

0.14

wine

0.14

Activations Density 0.184%

references to roles, positions, and career transitions in various professional contexts

No Comments

No Known Activations