INDEX

Explanations

code snippets and programming-related elements, particularly in relation to actions and methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

lius

-0.17

imbus

-0.15

Î¬

-0.15

CUS

-0.15

urch

-0.14

zdy

-0.14

ettings

-0.14

_FMT

-0.14

etri

-0.13

alm

-0.13

POSITIVE LOGITS

 Jacques

0.15

 æĮ

0.15

pul

0.15

 AssemblyFileVersion

0.14

 Peyton

0.14

Ä±f

0.14

 Petite

0.14

ÏĢÎ¿Ïħ

0.13

 kÄ±s

0.13

à¸ŀà¸¢

0.13

Activations Density 0.005%

code snippets and programming-related elements, particularly in relation to actions and methods

No Comments

No Known Activations