INDEX

Explanations

references to the name "Bert" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 Lear

-0.17

uce

-0.16

ÑĢÐ¾Ð²Ð¸Ñĩ

-0.16

dra

-0.15

kn

-0.14

ZN

-0.14

/***************************************************************************↵

-0.14

ä½ľ

-0.13

uze

-0.13

çķ

-0.13

POSITIVE LOGITS

Ì£

0.15

ician

0.14

arker

0.14

WISE

0.14

shire

0.14

 instruction

0.14

quot

0.14

 Ø§ÙĦØ¸

0.14

 newcom

0.13

 Wich

0.13

Activations Density 0.008%

references to the name "Bert" in various contexts

No Comments

No Known Activations