INDEX

Explanations

references to missing opportunities or information

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

ilogy

-0.17

 Spicer

-0.17

ponge

-0.15

è¡

-0.15

zem

-0.14

deer

-0.14

haul

-0.14

urga

-0.13

iddy

-0.13

kers

-0.13

POSITIVE LOGITS

 missed

0.36

miss

0.30

 misses

0.28

 lost

0.28

 miss

0.28

 potential

0.26

 missing

0.26

 opportunity

0.25

Miss

0.24

MISS

0.24

Activations Density 0.169%

references to missing opportunities or information

No Comments

No Known Activations