INDEX

Explanations

programming-related tokens and parameters in configuration files

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 */;↵

-0.15

å¦Ļ

-0.15

Mou

-0.14

PLY

-0.14

hek

-0.14

assel

-0.14

loub

-0.14

istributions

-0.14

ingo

-0.13

 Utilities

-0.13

POSITIVE LOGITS

ubble

0.16

roke

0.16

force

0.16

 Enable

0.16

 enable

0.16

 enabled

0.15

éĬĢ

0.15

æİ¨

0.15

 force

0.15

 Default

0.15

Activations Density 0.063%

programming-related tokens and parameters in configuration files

No Comments

No Known Activations