INDEX

Explanations

phrases related to sides, side effects, or side features in 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 @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

stery

-0.15

 hart

-0.15

lap

-0.15

-0.14

ospace

-0.14

reader

-0.14

uspend

-0.14

inker

-0.13

Transpose

-0.13

POSITIVE LOGITS

jÅ¡ÃŃ

0.17

rzy

0.15

ObjectContext

0.15

agento

0.15

ÐºÑĢÐµÑĤ

0.15

@brief

0.15

uyá»ĩt

0.15

ekk

0.15

ARRANT

0.14

ardo

0.14

Activations Density 0.038%

phrases related to sides, side effects, or side features in various contexts

No Comments

No Known Activations