INDEX

Explanations

geographic locations involving street names and directions

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

ument

-0.16

sten

-0.16

naire

-0.15

rine

-0.15

aper

-0.15

dept

-0.14

utton

-0.14

FAQ

-0.14

xin

-0.14

ropolis

-0.14

POSITIVE LOGITS

bound

0.16

OOD

0.15

anj

0.15

-assets

0.15

 Main

0.15

gate

0.15

entai

0.14

.protobuf

0.14

ilton

0.14

Ð¾ÑģÑĤÐ°ÑĤ

0.14

Activations Density 0.017%

geographic locations involving street names and directions

No Comments

No Known Activations