INDEX

Explanations

mathematical terms and operations related to limits and continuity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

pri

-0.15

izer

-0.14

dam

-0.14

Åĳ

-0.13

kd

-0.13

(Parcel

-0.13

 sexes

-0.13

 Neon

-0.13

rix

-0.13

obo

-0.13

POSITIVE LOGITS

storeId

0.15

omb

0.15

uss

0.14

APIView

0.14

.syn

0.14

stoff

0.14

íĺ

0.14

à¸´à¸į

0.14

PLUGIN

0.14

 Roller

0.14

Activations Density 0.080%

mathematical terms and operations related to limits and continuity

No Comments

No Known Activations