INDEX

Explanations

instances of the word "high" and related phrases indicating superior quality or performance

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Bentley

-0.14

itis

-0.14

yr

-0.14

ourn

-0.14

ote

-0.14

avors

-0.14

icont

-0.14

_PENDING

-0.14

omore

-0.13

Ã£n

-0.13

POSITIVE LOGITS

-performance

0.24

-resolution

0.22

 definition

0.21

performance

0.21

speed

0.20

strength

0.20

-speed

0.20

-eff

0.20

resolution

0.20

 resolution

0.19

Activations Density 0.046%

instances of the word "high" and related phrases indicating superior quality or performance

No Comments

No Known Activations