INDEX

Explanations

the name "Benjamin" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

toy

-0.16

artment

-0.15

ãĥ³ãĥī

-0.14

mund

-0.14

uction

-0.14

ustos

-0.14

ATTRIBUTE

-0.14

tle

-0.14

lad

-0.14

kinson

-0.14

POSITIVE LOGITS

 Franklin

0.27

 Netanyahu

0.19

Ð½ÑĮÐ¾

0.16

intl

0.16

Frank

0.15

 WCHAR

0.15

gÄ±n

0.14

ORD

0.14

ignon

0.14

Activations Density 0.012%

the name "Benjamin" in various contexts

No Comments

No Known Activations