INDEX

Explanations

references to context in a discussion or argument

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ades

-0.19

ë¯

-0.18

head

-0.18

Ø¯Ùĩ

-0.17

aps

-0.16

hti

-0.16

Å¥

-0.16

ibri

-0.15

 Hanson

-0.15

ery

-0.15

POSITIVE LOGITS

ually

0.47

ual

0.44

uality

0.34

UAL

0.30

MenuStrip

0.27

uali

0.20

uate

0.20

uale

0.20

uales

0.19

.SpringBootTest

0.19

Activations Density 0.032%

references to context in a discussion or argument

No Comments

No Known Activations