INDEX

Explanations

mentions of numerical values, particularly those related to data or dimensions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

warts

-0.19

ted

-0.16

-0.15

rev

-0.15

iaux

-0.15

ri

-0.14

Ð¼Ð°Ð·

-0.14

amo

-0.14

.nz

-0.14

POSITIVE LOGITS

iÃ¨me

0.27

fold

0.25

Fold

0.21

ToOne

0.19

-dimensional

0.17

ieme

0.17

-fold

0.16

-handed

0.15

isted

0.15

ityEngine

0.15

Activations Density 0.069%

mentions of numerical values, particularly those related to data or dimensions

No Comments

No Known Activations