INDEX

Explanations

concessive phrases that indicate contrast or qualification

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

amo

-0.15

Äįka

-0.14

owie

-0.14

 Trafford

-0.14

orgia

-0.14

ì§ĵ

-0.14

andre

-0.14

geme

-0.14

_pa

-0.14

lle

-0.13

POSITIVE LOGITS

rek

0.16

apus

0.16

webtoken

0.15

 Morm

0.14

-thumbnails

0.14

ashi

0.14

ey

0.14

Mev

0.14

ButtonItem

0.13

Ã¡Å¡

0.13

Activations Density 0.045%

concessive phrases that indicate contrast or qualification

No Comments

No Known Activations