INDEX

Explanations

punctuation and formatting elements within code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

igu

-0.15

odes

-0.15

amarin

-0.14

ilm

-0.14

RoutingModule

-0.14

atti

-0.14

artz

-0.13

ħn

-0.13

DRV

-0.13

 combination

-0.13

POSITIVE LOGITS

Kou

0.15

_codegen

0.15

conti

0.15

 fitte

0.15

icum

0.14

ipher

0.14

Ð»Ð°Ð´Ð°

0.14

ë¹ĦìķĦ

0.14

.opend

0.14

croll

0.13

Activations Density 0.025%

punctuation and formatting elements within code

No Comments

No Known Activations