INDEX

Explanations

occurrences of various coding terms and structures

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ss

-0.17

ternet

-0.16

rema

-0.16

shi

-0.15

name

-0.15

Yaz

-0.14

most

-0.14

reo

-0.14

 =============================================================================↵

-0.14

ships

-0.14

POSITIVE LOGITS

ummings

0.18

çłģ

0.17

eer

0.17

ç¢¼

0.17

velopment

0.16

incinn

0.16

entities

0.15

ATALOG

0.15

"default

0.15

éļľ

0.14

Activations Density 0.049%

occurrences of various coding terms and structures

No Comments

No Known Activations