INDEX

Explanations

expressions of grief or emotional responses to traumatic events

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

 irritating

-0.17

 hilarious

-0.17

 irrit

-0.17

å¦Ļ

-0.17

Å¾ÃŃ

-0.17

uintptr

-0.16

 crippling

-0.15

 hilar

-0.15

ronic

-0.15

 annoy

-0.15

POSITIVE LOGITS

 horror

0.29

hor

0.28

 graphic

0.26

hor

0.25

Hor

0.24

Hor

0.23

 Horror

0.23

sad

0.23

 horrific

0.23

 horrible

0.23

Activations Density 0.451%

expressions of grief or emotional responses to traumatic events

No Comments

No Known Activations