INDEX

Explanations

references to programming concepts and code components

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

 actionTypes

-0.16

 Ã¶den

-0.16

rais

-0.15

INavigation

-0.15

erland

-0.15

evi

-0.15

 ActionTypes

-0.15

Ã£i

-0.14

Convertible

-0.14

baugh

-0.14

POSITIVE LOGITS

ILI

0.17

à¸Ńà¸Ļ

0.16

fern

0.15

gi

0.14

phony

0.14

ÎµÏħ

0.14

ampions

0.14

isan

0.13

Activations Density 0.393%

references to programming concepts and code components

No Comments

No Known Activations