INDEX

Explanations

terms related to nerves and nerve injuries

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

otte

-0.15

spot

-0.15

edom

-0.15

.cast

-0.15

é¼»

-0.14

 Ston

-0.14

ailer

-0.14

-spot

-0.13

FO

-0.13

WA

-0.13

POSITIVE LOGITS

 nerve

0.47

 nerves

0.40

 nerv

0.28

ner

0.25

 Ð½ÐµÑĢÐ²

0.25

 nervous

0.25

gang

0.23

 gang

0.23

inn

0.22

ner

0.21

Activations Density 0.057%

terms related to nerves and nerve injuries

No Comments

No Known Activations