INDEX

Explanations

terms related to behavior and behavioral interventions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ye

-0.19

yan

-0.17

ars

-0.16

xin

-0.16

ya

-0.15

isons

-0.15

work

-0.15

enny

-0.15

uj

-0.14

POSITIVE LOGITS

ally

0.31

ial

0.24

IAL

0.19

 patterns

0.18

ALLY

0.18

alist

0.18

istically

0.17

istic

0.16

isms

0.16

alf

0.16

Activations Density 0.021%

terms related to behavior and behavioral interventions

No Comments

No Known Activations