INDEX

Explanations

phrases indicating frequency of occurrences or repetitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ridge

-0.19

ship

-0.17

set

-0.16

ness

-0.16

rex

-0.15

endo

-0.15

type

-0.15

/Data

-0.14

izio

-0.14

à¤¾à¤£

-0.14

POSITIVE LOGITS

 times

0.33

-times

0.29

hare

0.24

 Times

0.22

 weekly

0.22

 TIMES

0.22

fold

0.21

times

0.21

(times

0.21

 daily

0.21

Activations Density 0.044%

phrases indicating frequency of occurrences or repetitions

No Comments

No Known Activations