INDEX

Explanations

assertive statements related to personal accountability and integrity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 yourselves

-0.16

rosse

-0.14

ãĤ¤

-0.14

ä¼Ĭ

-0.13

—we

-0.13

iye

-0.13

 youre

-0.13

forman

-0.13

 themselves

-0.13

ross

-0.13

POSITIVE LOGITS

my

0.82

 myself

0.77

æĪĳçļĦ

0.69

æĪĳ

0.68

 saya

0.64

 tÃ´i

0.63

 mijn

0.60

æĺ¯æĪĳ

0.60

è®©æĪĳ

0.58

my

0.57

Activations Density 4.108%

assertive statements related to personal accountability and integrity

No Comments

No Known Activations