INDEX

Explanations

occurrences of the word "in"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

sofar

-0.21

 relation

-0.20

relation

-0.19

ved

-0.19

reo

-0.18

agar

-0.17

 Relation

-0.17

duct

-0.17

 regards

-0.16

inder

-0.16

POSITIVE LOGITS

 truth

0.27

 typical

0.21

 true

0.19

truth

0.18

 reality

0.18

istrovstvÃŃ

0.16

 characteristic

0.15

ä¸Ģé¡µ

0.15

 spirit

0.15

_truth

0.15

Activations Density 0.102%

occurrences of the word "in"

No Comments

No Known Activations