INDEX

Explanations

statements expressing moral judgment or inconsistency over time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ÅĦ

-0.16

Ð°ÑĢÑĩ

-0.15

erte

-0.15

erer

-0.14

brero

-0.14

ivol

-0.14

ãĥ¼ãĥ³

-0.14

eria

-0.14

Ø§ÙĪÙĬ

-0.14

Î¼Î·

-0.14

POSITIVE LOGITS

ä»Ĭ

0.19

 continue

0.18

_now

0.17

 current

0.17

 today

0.17

 continues

0.17

today

0.16

 ä»Ĭ

0.16

.now

0.16

current

0.16

Activations Density 0.145%

statements expressing moral judgment or inconsistency over time

No Comments

No Known Activations