INDEX

Explanations

negative prefixes or variations of the word "un"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

actively

-0.18

aft

-0.16

acic

-0.16

alet

-0.16

dev

-0.15

deo

-0.15

GLOBALS

-0.15

aret

-0.15

 Ð·Ð°Ð¿Ð°Ñģ

-0.14

/DD

-0.14

POSITIVE LOGITS

ione

0.19

ertainty

0.18

esco

0.18

ites

0.17

anny

0.17

 Myst

0.16

idade

0.15

ecessarily

0.15

iÃ³n

0.15

(Un

0.15

Activations Density 0.041%

negative prefixes or variations of the word "un"

No Comments

No Known Activations