INDEX

Explanations

proper nouns related to geography and significant locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

fare

-0.16

ippy

-0.16

rait

-0.16

rou

-0.15

 fare

-0.15

 Mehr

-0.15

 prive

-0.14

 Fare

-0.14

 privileged

-0.14

ter

-0.14

POSITIVE LOGITS

okrat

0.18

Ø®Ø§ÙĨÙĩ

0.16

SKTOP

0.16

getManager

0.15

reesome

0.15

ì¦Ŀ

0.15

ONGL

0.15

.cmb

0.15

ÙĦÙĤ

0.15

recio

0.15

Activations Density 0.393%

proper nouns related to geography and significant locations

No Comments

No Known Activations