INDEX

Explanations

mentions of the name "Bor" or variations related to it

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

áº£ng

-0.16

Zuk

-0.16

 smoking

-0.16

ti

-0.15

 Ronaldo

-0.15

ÑĨÑİ

-0.15

ç«¥

-0.14

ITTER

-0.14

nos

-0.14

 Smoking

-0.14

POSITIVE LOGITS

Bor

0.19

finger

0.18

OUGH

0.17

owie

0.17

ussia

0.17

utut

0.17

rego

0.16

zeit

0.16

islav

0.16

rows

0.16

Activations Density 0.012%

mentions of the name "Bor" or variations related to it

No Comments

No Known Activations