INDEX

Explanations

phrases related to quality and standards 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 @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

orp

-0.17

otech

-0.14

iever

-0.14

ä¹Łæĺ¯

-0.14

entials

-0.14

.addElement

-0.13

.cbo

-0.13

ongsTo

-0.13

isko

-0.13

POSITIVE LOGITS

etc

0.25

etc

0.23

 finally

0.23

 importantly

0.21

 overall

0.21

 ultimately

0.18

overall

0.18

 even

0.17

Lastly

0.16

 generally

0.16

Activations Density 0.437%

phrases related to quality and standards in various contexts

No Comments

No Known Activations