INDEX

Explanations

mathematical symbols and expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

endencies

-0.16

-0.15

deki

-0.14

 Werner

-0.14

 Lance

-0.14

ignon

-0.14

chet

-0.14

$_

-0.14

ula

-0.14

amac

-0.14

POSITIVE LOGITS

åĢį

0.17

ï½¥

0.17

pir

0.15

 McInt

0.15

["$

0.15

pter

0.14

 helicopt

0.14

.scalablytyped

0.14

ADIO

0.13

/person

0.13

Activations Density 0.073%

mathematical symbols and expressions

No Comments

No Known Activations