INDEX

Explanations

location addresses and geographic identifiers

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

ppe

-0.18

vik

-0.16

rne

-0.15

ksen

-0.14

olk

-0.14

arme

-0.13

elsey

-0.13

 Folk

-0.13

xm

-0.13

POSITIVE LOGITS

iar

0.16

ucha

0.15

 parcel

0.14

outine

0.14

ilih

0.14

setItem

0.14

 OnTrigger

0.14

BJ

0.13

lest

0.13

eta

0.13

Activations Density 0.080%

location addresses and geographic identifiers

No Comments

No Known Activations