INDEX

Explanations

phrases related to death and medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 DEAD

-0.19

.docs

-0.16

 Dead

-0.16

-destruct

-0.16

Dead

-0.15

(dead

-0.15

ÐµÑĢÑĮ

-0.15

ilim

-0.15

destruct

-0.15

abcdefghijklmnop

-0.14

POSITIVE LOGITS

 complications

0.25

 causes

0.23

 suff

0.23

 natural

0.22

 starvation

0.21

 heart

0.19

 cause

0.19

 overdose

0.19

">//

0.18

 drowning

0.18

Activations Density 0.074%

phrases related to death and medical conditions

No Comments

No Known Activations