INDEX

Explanations

code-related terms and references that indicate processing or interacting with data structures and commands

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

 Smith

-0.15

nor

-0.14

mere

-0.13

 simply

-0.13

rea

-0.13

aram

-0.13

Smith

-0.13

 Weiner

-0.13

 scre

-0.13

 Mach

-0.13

POSITIVE LOGITS

ãĥĭãĥĥãĤ¯

0.15

istrovstvÃŃ

0.15

.grade

0.14

plib

0.14

Ð¾Ð»ÑĮÐ·Ð¾Ð²Ð°ÑĤ

0.14

dbuf

0.14

Hun

0.14

akov

0.13

zac

0.13

âĢĮÙ¾

0.13

Activations Density 0.095%

code-related terms and references that indicate processing or interacting with data structures and commands

No Comments

No Known Activations