INDEX

Explanations

references to geographic locations and local government entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

uent

-0.17

evi

-0.16

 Canyon

-0.14

´Ŀ

-0.14

theless

-0.14

ort

-0.14

wr

-0.14

Ð¶Ð´

-0.14

Äħd

-0.14

.DeepEqual

-0.14

POSITIVE LOGITS

 county

0.26

 County

0.25

shire

0.24

ashire

0.20

county

0.20

County

0.18

 Regiment

0.18

pps

0.18

orks

0.18

 counties

0.17

Activations Density 0.032%

references to geographic locations and local government entities

No Comments

No Known Activations