INDEX

Explanations

phrases introducing examples or instances, often indicated by the word "for"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

inding

-0.17

imals

-0.15

ãĥĭãĥĥãĤ¯

-0.15

entiful

-0.15

ãĥ¼ãĥ«ãĥī

-0.14

 Ø³Ø®

-0.14

NSNotification

-0.14

vang

-0.14

 kostenlose

-0.14

ÃŃm

-0.14

POSITIVE LOGITS

oday

0.18

unately

0.17

Ø³ØªØ±

0.16

 reasons

0.15

rant

0.15

Ø§Ø¬Ø§Øª

0.15

reason

0.14

 instance

0.14

 reason

0.14

us

0.14

Activations Density 0.078%

phrases introducing examples or instances, often indicated by the word "for"

No Comments

No Known Activations