INDEX

Explanations

words indicating possession or ownership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

gee

-0.15

lac

-0.14

BOX

-0.14

 HÃł

-0.14

anÃ¡

-0.14

 Fountain

-0.13

Hob

-0.13

Box

-0.13

wing

-0.13

POSITIVE LOGITS

comma

0.16

.localized

0.16

erken

0.15

ãĥ¼ãĥĵ

0.15

itler

0.15

 Verde

0.14

hap

0.14

aland

0.14

 ÑĢÐ¾Ñģ

0.14

stantiate

0.14

Activations Density 0.015%

words indicating possession or ownership

No Comments

No Known Activations