INDEX

Explanations

occurrences of the word "We" and its variants in the text

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

Ø¹ÛĮ

-0.16

 figuring

-0.15

precated

-0.14

WARDED

-0.14

 Lilly

-0.14

ampa

-0.14

aghetti

-0.14

cept

-0.14

vier

-0.14

opia

-0.13

POSITIVE LOGITS

 note

0.19

 caution

0.17

 term

0.17

 wish

0.16

 remark

0.16

 defer

0.16

 adher

0.15

 refer

0.15

 stress

0.15

Activations Density 0.078%

occurrences of the word "We" and its variants in the text

No Comments

No Known Activations