INDEX

Explanations

technical terms related to configuration and data structure definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

onec

-0.14

hashCode

-0.14

-pagination

-0.13

idis

-0.13

 activeClassName

-0.13

ania

-0.12

æĭľ

-0.12

 Interr

-0.12

StyleSheet

-0.12

inkel

-0.12

POSITIVE LOGITS

 field

0.79

 fields

0.71

 Field

0.68

-field

0.63

field

0.63

Field

0.62

 FIELD

0.60

_field

0.59

 Fields

0.59

fields

0.54

Activations Density 0.224%

technical terms related to configuration and data structure definitions

No Comments

No Known Activations