INDEX

Explanations

terms indicating consensus or collective agreement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

PullParser

-0.16

ÑĩÐ¸Ð»Ð¸

-0.15

idla

-0.15

Å¡ti

-0.15

 MÃ¤r

-0.15

CTOR

-0.14

ãĤ

-0.14

luÅ¾

-0.14

teg

-0.14

ArgumentException

-0.14

POSITIVE LOGITS

 tran

0.17

uario

0.15

ities

0.15

 popular

0.15

Ecc

0.15

ed

0.14

Eis

0.14

lip

0.14

Activations Density 0.003%

terms indicating consensus or collective agreement

No Comments

No Known Activations