INDEX

Explanations

references to friendships and close relationships

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

okit

-0.18

æĢģ

-0.15

à¸Ńà¸¥

-0.14

adolu

-0.14

Creators

-0.14

enderit

-0.14

immers

-0.13

kea

-0.13

_ghost

-0.13

aille

-0.13

POSITIVE LOGITS

 friends

0.60

 friend

0.52

 pals

0.48

 FRIEND

0.48

friends

0.46

æľĭåıĭ

0.45

 buddies

0.44

 Friends

0.43

riends

0.43

 friendships

0.41

Activations Density 0.164%

references to friendships and close relationships

No Comments

No Known Activations