INDEX

Explanations

punctuation marks, especially question marks and periods

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

iyat

-0.15

BuilderInterface

-0.15

ulp

-0.15

pul

-0.15

iÄĻ

-0.14

tparam

-0.14

Sor

-0.14

AccessException

-0.14

 Kemp

-0.14

 Nationwide

-0.14

POSITIVE LOGITS

.cv

0.16

ernet

0.15

 Mattis

0.15

 semiclassical

0.15

0.14

 gravity

0.14

 Grimm

0.14

essler

0.14

 Quartz

0.14

TRL

0.14

Activations Density 0.062%

punctuation marks, especially question marks and periods

No Comments

No Known Activations