INDEX

Explanations

references to biochemical mechanisms and interactions, particularly involving neurotransmitters and receptors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

instein

-0.14

kas

-0.14

 Greenwich

-0.14

amax

-0.14

RSS

-0.14

rement

-0.14

Ø®Ø·

-0.14

æºĲ

-0.13

him

-0.13

_required

-0.12

POSITIVE LOGITS

 receptor

0.39

 receptors

0.38

 agon

0.27

ceptors

0.26

 recept

0.26

ceptor

0.25

 recep

0.24

 receivers

0.24

 reception

0.23

 subtype

0.23

Activations Density 0.021%

references to biochemical mechanisms and interactions, particularly involving neurotransmitters and receptors

No Comments

No Known Activations