INDEX

Explanations

phrases that indicate instructions, obligations, or requirements imposed on groups or individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

Ø±ÙĪØ¯

-0.17

 VÃ¡c

-0.17

itsu

-0.15

erer

-0.15

ÃŃg

-0.15

rang

-0.15

Latch

-0.15

 ZÃ¡p

-0.15

/epl

-0.15

ãĤĤãģĨ

-0.14

POSITIVE LOGITS

 encouraged

0.29

 allowed

0.25

 given

0.22

 asked

0.22

 required

0.22

 encour

0.22

allowed

0.22

 expected

0.22

 urged

0.21

Asked

0.20

Activations Density 0.179%

phrases that indicate instructions, obligations, or requirements imposed on groups or individuals

No Comments

No Known Activations