INDEX

Explanations

numerical calculations and relationships involving numeric data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

aÃ±a

-0.17

oise

-0.16

OrDefault

-0.15

lock

-0.13

cab

-0.13

 Karn

-0.13

 drag

-0.13

ockey

-0.13

 Missouri

-0.13

POSITIVE LOGITS

.amazonaws

0.17

ivet

0.16

OKIE

0.15

ulumi

0.14

UInteger

0.14

 RouteServiceProvider

0.14

irut

0.14

TestingModule

0.14

STYPE

0.14

Activations Density 0.031%

numerical calculations and relationships involving numeric data

No Comments

No Known Activations