INDEX

Explanations

names and identifiers associated with various entities

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

upply

-0.15

privileged

-0.14

/location

-0.14

ãĤ¿ãĤ¤

-0.14

ç±

-0.14

uche

-0.13

 favicon

-0.13

.Escape

-0.13

stagram

-0.13

POSITIVE LOGITS

udev

0.15

grave

0.15

Æ°á»£ng

0.14

YRO

0.14

antro

0.14

	Copyright

0.14

laÅŁ

0.13

atti

0.13

iale

0.13

ippet

0.13

Activations Density 0.305%

names and identifiers associated with various entities

No Comments

No Known Activations

names and identifiers associated with various entities

No Comments

No Known Activations