INDEX

Explanations

references to empty states or checks for null conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ENO

-0.15

ded

-0.14

bes

-0.14

enas

-0.14

uff

-0.14

ds

-0.14

cid

-0.14

leared

-0.14

enia

-0.14

ocz

-0.13

POSITIVE LOGITS

oho

0.18

anter

0.17

Verdana

0.14

 Erotische

0.14

marshall

0.14

akens

0.14

ojis

0.14

ATTER

0.14

oko

0.13

sbin

0.13

Activations Density 0.017%

references to empty states or checks for null conditions

No Comments

No Known Activations