INDEX

Explanations

repetitions of the pronoun "he"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ly

-0.20

 itself

-0.20

less

-0.16

otte

-0.16

ousel

-0.15

ouri

-0.15

andes

-0.15

wo

-0.15

rette

-0.15

onne

-0.15

POSITIVE LOGITS

/she

0.49

/her

0.39

 himself

0.39

aviest

0.34

inous

0.32

'll

0.31

’ll

0.30

’d

0.29

'd

0.29

aped

0.28

Activations Density 0.211%

repetitions of the pronoun "he"

No Comments

No Known Activations