INDEX

Explanations

phrases identifying differences or distinctions between two concepts or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

.relationship

-0.15

rys

-0.15

iazza

-0.15

uhl

-0.15

EntryPoint

-0.15

ury

-0.14

USTOM

-0.14

ading

-0.14

 Masc

-0.14

 neither

-0.14

POSITIVE LOGITS

aiser

0.15

chia

0.15

izards

0.15

ONO

0.14

amedi

0.14

upert

0.14

 HÃ¤

0.14

inputEmail

0.14

 Ãľl

0.14

iates

0.14

Activations Density 0.055%

phrases identifying differences or distinctions between two concepts or items

No Comments

No Known Activations