INDEX

Explanations

phrases indicating achievement or accomplishment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

mtree

-0.17

ubl

-0.17

ASI

-0.15

 Gone

-0.15

icina

-0.14

 Ð¿Ð¾Ð½

-0.14

ampp

-0.14

dana

-0.14

itored

-0.14

 cref

-0.14

POSITIVE LOGITS

 somehow

0.20

 somew

0.18

-ÑĤÐ°ÐºÐ¸

0.17

 manages

0.16

get

0.16

 enough

0.15

Ded

0.15

 managed

0.15

gu

0.14

Activations Density 0.044%

phrases indicating achievement or accomplishment

No Comments

No Known Activations