INDEX

Explanations

references to upgrading or enhancing items or experiences

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

arty

-0.19

nÃ¡m

-0.14

xia

-0.14

 rÃ¡

-0.13

opy

-0.13

ekler

-0.13

hÃ¡

-0.13

ocks

-0.13

 Resume

-0.13

stalk

-0.13

POSITIVE LOGITS

'gc

0.19

/down

0.16

 semiclass

0.15

 AssemblyVersion

0.14

orus

0.14

Connell

0.14

èĤ¥

0.14

DDS

0.13

/close

0.13

Activations Density 0.011%

references to upgrading or enhancing items or experiences

No Comments

No Known Activations