INDEX

Explanations

terms related to depth measurement and physical constraints in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÎµÏħ

-0.16

ensburg

-0.15

á»Ńa

-0.15

airo

-0.15

à¥ĭà¤·

-0.14

 distra

-0.13

artner

-0.12

Clr

-0.12

 ============================================================================↵

-0.12

POSITIVE LOGITS

 deep

1.35

deep

1.23

 Deep

1.19

Deep

1.16

 depth

1.12

æ·±

1.10

 deeper

1.05

 deepest

1.03

depth

1.02

 Depth

1.01

Activations Density 0.372%

terms related to depth measurement and physical constraints in various contexts

No Comments

No Known Activations