INDEX

Explanations

references to specific files and data structures in programming, as well as terms related to documentation and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

Lua

-0.14

indre

-0.13

 memcmp

-0.13

oufl

-0.13

.cfg

-0.13

aley

-0.13

avaÅŁ

-0.12

IRTH

-0.12

BufferSize

-0.12

Ã©f

-0.12

POSITIVE LOGITS

ramid

0.14

 prostitut

0.13

elt

0.13

enson

0.13

inha

0.13

à¸¸à¸ķ

0.13

artisan

0.13

ĨĴ

0.13

inspace

0.12

Î¾Î¹

0.12

Activations Density 0.063%

references to specific files and data structures in programming, as well as terms related to documentation and regulations

No Comments

No Known Activations