INDEX

Explanations

names of family members and relationships

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

ions

-0.16

utor

-0.15

 mass

-0.15

lob

-0.15

ator

-0.15

mass

-0.15

pair

-0.14

Ans

-0.14

icator

-0.14

 pair

-0.13

POSITIVE LOGITS

isy

0.17

ostel

0.16

tiles

0.15

wine

0.15

gaard

0.14

IPA

0.14

CallBack

0.14

å¤®

0.14

Activations Density 0.018%

names of family members and relationships

No Comments

No Known Activations