INDEX

Explanations

proper nouns, particularly names and titles

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

ãĢħ

-0.14

Ø´Ùĩ

-0.13

 samo

-0.13

ãģłãģ£ãģ¦

-0.13

ppers

-0.13

 itself

-0.12

IconModule

-0.12

ButtonModule

-0.12

IGO

-0.12

-Ñı

-0.11

POSITIVE LOGITS

who

0.52

 whom

0.47

who

0.45

Jr

0.45

's

0.45

’s

0.39

‘s

0.38

 whose

0.38

—who

0.37

Sr

0.36

Activations Density 0.343%

proper nouns, particularly names and titles

No Comments

No Known Activations