INDEX

Explanations

comments and annotations in code

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

appa

-0.15

apa

-0.15

LIB

-0.14

ses

-0.14

Bow

-0.14

ayed

-0.14

apis

-0.13

ãģ¥

-0.13

amba

-0.13

oot

-0.13

POSITIVE LOGITS

tega

0.17

Ì§

0.16

Î´ÏĮÎ½

0.16

anz

0.16

 Hatch

0.16

_dummy

0.16

uder

0.15

olid

0.15

Å¡il

0.15

.CV

0.14

Activations Density 0.065%

comments and annotations in code

No Comments

No Known Activations