INDEX

Explanations

emotional expressions and interactions among characters

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

agan

-0.17

Ä¾

-0.16

 fart

-0.16

ogn

-0.15

emales

-0.14

 Info

-0.14

 area

-0.14

èĩ£

-0.14

 Britain

-0.14

POSITIVE LOGITS

 queer

0.20

 callers

0.16

[P

0.15

etur

0.15

/GPL

0.14

æ´²

0.14

 Pussy

0.14

 Weed

0.14

 Perc

0.14

-girl

0.14

Activations Density 0.118%

emotional expressions and interactions among characters

No Comments

No Known Activations