INDEX

Explanations

names or titles associated with notable individuals or 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

OE

-0.16

elyn

-0.15

reater

-0.14

ilig

-0.13

íı°

-0.13

 Hlav

-0.13

McD

-0.13

procs

-0.13

POSITIVE LOGITS

avo

0.15

RAINT

0.14

KG

0.14

uish

0.14

idth

0.14

im

0.14

Ø¹Ø§

0.14

/rfc

0.14

uff

0.14

 push

0.14

Activations Density 0.011%

names or titles associated with notable individuals or entities

No Comments

No Known Activations