INDEX

Explanations

the repeated mention of "mach" with varying numerical values associated with it, indicating a focus on instances related to "mach" as a key concept or term

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 dime

-0.15

Diy

-0.15

klÃ¤

-0.15

oggler

-0.15

ILog

-0.14

Ã³s

-0.14

zens

-0.14

leyen

-0.14

askets

-0.14

ctions

-0.14

POSITIVE LOGITS

inations

0.24

ismo

0.22

anical

0.21

inery

0.20

etes

0.18

hap

0.18

intosh

0.18

 mach

0.18

 Mach

0.17

ete

0.17

Activations Density 0.004%

the repeated mention of "mach" with varying numerical values associated with it, indicating a focus on instances related to "mach" as a key concept or term

No Comments

No Known Activations