INDEX

Explanations

terms related to nerves and neurological conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

otas

-0.17

eko

-0.16

ÏĥÎ¹Î¼Î¿

-0.16

culate

-0.15

stinence

-0.15

itsu

-0.15

 Straw

-0.15

-corner

-0.14

ileo

-0.14

.nano

-0.14

POSITIVE LOGITS

arb

0.15

zd

0.15

motor

0.14

æŁ±

0.14

OutOfRange

0.14

 motor

0.14

ollar

0.14

 Motor

0.13

XF

0.13

 bulk

0.13

Activations Density 0.031%

terms related to nerves and neurological conditions

No Comments

No Known Activations