INDEX

Explanations

instances of the pronoun 'it' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

(es

-0.20

hart

-0.18

have

-0.17

Ùĩ

-0.16

ology

-0.16

hip

-0.15

ÙĨØ¯Ùĩ

-0.15

ified

-0.14

hg

-0.14

POSITIVE LOGITS

iner

0.44

chy

0.38

unes

0.36

's

0.31

’s

0.28

alic

0.28

inerary

0.28

'll

0.27

ching

0.27

aly

0.27

Activations Density 0.402%

instances of the pronoun 'it' in various contexts

No Comments

No Known Activations