INDEX

Explanations

mathematical expressions and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ADDE

-0.18

raman

-0.16

 Downs

-0.15

inqu

-0.15

ingerprint

-0.15

uels

-0.14

ipment

-0.14

idata

-0.14

 interp

-0.14

ongyang

-0.14

POSITIVE LOGITS

 Little

0.18

asca

0.18

.persistent

0.15

ulia

0.14

Little

0.13

jour

0.13

MUT

0.13

ourcem

0.13

FINITE

0.13

weetalert

0.13

Activations Density 0.177%

mathematical expressions and symbols

No Comments

No Known Activations