INDEX

Explanations

punctuation and formatting marks in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

usk

-0.15

OfSize

-0.15

 Vict

-0.15

coli

-0.14

izzling

-0.14

abal

-0.14

.bp

-0.14

gere

-0.13

 ãĢī

-0.13

utow

-0.13

POSITIVE LOGITS

anax

0.17

PTY

0.16

idi

0.15

LOPT

0.15

elho

0.15

appa

0.15

 ãĥĿ

0.15

aco

0.14

andler

0.14

/host

0.14

Activations Density 0.116%

punctuation and formatting marks in text

No Comments

No Known Activations