INDEX

Explanations

references to family 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 @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

Friend

-0.15

deniz

-0.14

ÑģÑĤÐ¾ÑĢ

-0.14

ugi

-0.14

iben

-0.14

rescia

-0.14

ancestor

-0.13

ahir

-0.13

ANJI

-0.13

POSITIVE LOGITS

 whom

0.23

 ages

0.22

 grown

0.21

 adopted

0.21

 attend

0.20

 twins

0.17

named

0.17

 attending

0.17

(named

0.17

age

0.17

Activations Density 0.179%

references to family and relationships

No Comments

No Known Activations