INDEX

Explanations

phrases indicating roles and positions held by individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

HIR

-0.20

aily

-0.15

hair

-0.15

era

-0.14

hee

-0.14

.hasOwnProperty

-0.14

íĭ

-0.14

atr

-0.14

prep

-0.14

emachine

-0.14

POSITIVE LOGITS

.scalablytyped

0.17

sher

0.16

illance

0.15

heck

0.15

CKER

0.14

omanip

0.14

sor

0.13

istrovstvÃŃ

0.13

arrants

0.13

HECK

0.13

Activations Density 0.028%

phrases indicating roles and positions held by individuals

No Comments

No Known Activations