INDEX

Explanations

terms related to morality and ethical evaluations of society

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

alon

-0.18

usto

-0.17

adil

-0.15

ÃŃÅ¡

-0.15

angan

-0.15

Bes

-0.14

oÅ¾

-0.14

 kÃ¶n

-0.14

hti

-0.13

ITTE

-0.13

POSITIVE LOGITS

idar

0.16

ible

0.16

iban

0.14

abwe

0.14

izoph

0.14

ģµ

0.14

ubern

0.14

inate

0.14

 properly

0.14

 modern

0.13

Activations Density 0.164%

terms related to morality and ethical evaluations of society

No Comments

No Known Activations