INDEX

Explanations

phrases and terms related to data analysis and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

Å¡ti

-0.15

Ø¯Ø§Ø¯

-0.15

eden

-0.15

iste

-0.14

dzi

-0.14

isia

-0.14

onest

-0.14

lie

-0.14

 Allen

-0.14

baÅŁ

-0.13

POSITIVE LOGITS

STRU

0.14

.RequestMethod

0.14

ãĥ«ãĥī

0.14

_firestore

0.14

éĺ¶

0.14

Ø±ÙĪÛĮ

0.14

ë¥

0.14

>window

0.14

0.13

 AssemblyVersion

0.13

Activations Density 0.259%

phrases and terms related to data analysis and statistics

No Comments

No Known Activations