INDEX

Explanations

references to death and significant life events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

-0.16

olumn

-0.16

ez

-0.15

 trÃł

-0.15

ALER

-0.14

.psi

-0.14

incer

-0.14

uisine

-0.14

bildung

-0.14

 longevity

-0.14

POSITIVE LOGITS

Ø±ÛĮØ§ÙĨ

0.14

 GOODMAN

0.14

zzle

0.14

yme

0.13

amel

0.13

erin

0.13

NOP

0.13

 Jarvis

0.13

Ð»Ð¸Ð²

0.13

ncmp

0.13

Activations Density 0.042%

references to death and significant life events

No Comments

No Known Activations