INDEX

Explanations

references to major entities, events, or concepts

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

sWith

-0.17

ery

-0.16

ires

-0.16

ableView

-0.15

etal

-0.15

äº¬éĥ½

-0.15

ray

-0.14

INSTANCE

-0.14

erson

-0.14

ych

-0.14

POSITIVE LOGITS

-league

0.32

/min

0.23

itarian

0.22

 league

0.22

league

0.20

League

0.18

 League

0.18

 leagues

0.18

redient

0.17

-League

0.17

Activations Density 0.028%

references to major entities, events, or concepts

No Comments

No Known Activations