INDEX

Explanations

phrases indicating the presence of diversity, challenges, and responsibilities within various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

lier

-0.18

nist

-0.16

 rekl

-0.15

ucas

-0.14

omanip

-0.13

esc

-0.13

erk

-0.13

sockopt

-0.13

adel

-0.13

 Wheel

-0.13

POSITIVE LOGITS

 existing

0.17

Dos

0.14

opak

0.14

ì¢Į

0.14

neu

0.14

ource

0.14

åĻ¨

0.14

oire

0.14

 argument

0.14

arg

0.14

Activations Density 0.101%

phrases indicating the presence of diversity, challenges, and responsibilities within various contexts

No Comments

No Known Activations