INDEX

Explanations

references to alphabets and writing systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

olas

-0.15

indy

-0.15

 Lens

-0.14

afil

-0.14

ago

-0.14

verb

-0.14

ugins

-0.14

Lens

-0.14

ordion

-0.14

aliz

-0.14

POSITIVE LOGITS

Ã¼rk

0.15

ENTIAL

0.14

Ã¹i

0.13

UCCESS

0.13

ÏĨÏĮ

0.13

ÙĪÙĦÙĬ

0.13

 sideline

0.13

ìĿ´ë¹Ħ

0.13

stoup

0.13

 corr

0.13

Activations Density 0.017%

references to alphabets and writing systems

No Comments

No Known Activations