INDEX

Explanations

references to the structure and function of the hippocampus in neuroscientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

IPH

-0.15

å¢Ļ

-0.15

untas

-0.15

_ABI

-0.15

êµ´

-0.14

 puck

-0.14

.pb

-0.14

 nuclei

-0.14

cih

-0.14

POSITIVE LOGITS

 excit

0.27

 pres

0.25

 posts

0.25

 terminals

0.24

Pur

0.23

 Projection

0.23

 projection

0.22

ax

0.22

-posts

0.22

syn

0.22

Activations Density 0.016%

references to the structure and function of the hippocampus in neuroscientific contexts

No Comments

No Known Activations