INDEX

Explanations

mentions of beneficence or beneficial actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ghi

-0.16

hop

-0.15

ÏĢÎ·

-0.15

otope

-0.15

aseline

-0.15

ieri

-0.15

orc

-0.14

locks

-0.14

-shadow

-0.14

ork

-0.14

POSITIVE LOGITS

volent

0.33

vol

0.25

iciary

0.21

ath

0.20

icial

0.20

icia

0.20

itting

0.19

ific

0.19

ift

0.18

fits

0.17

Activations Density 0.009%

mentions of beneficence or beneficial actions

No Comments

No Known Activations