INDEX

Explanations

code-related terms and variable assignments in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

gia

-0.15

ADA

-0.15

 Kidd

-0.14

 Vander

-0.14

 Chung

-0.14

reek

-0.14

utoff

-0.13

 Huck

-0.13

Ts

-0.13

ky

-0.13

POSITIVE LOGITS

wal

0.18

idal

0.15

nul

0.15

atti

0.15

egers

0.14

aniel

0.14

azure

0.13

 Attachment

0.13

WAL

0.13

SG

0.13

Activations Density 0.012%

code-related terms and variable assignments in programming contexts

No Comments

No Known Activations