INDEX

Explanations

references to governance and organized groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ERNEL

-0.15

Included

-0.15

rypto

-0.15

 Serialized

-0.15

ttp

-0.15

ëĮ

-0.14

igne

-0.14

atos

-0.13

rar

-0.13

phins

-0.12

POSITIVE LOGITS

led

0.91

Led

0.71

led

0.66

 headed

0.66

 lead

0.65

Led

0.65

lead

0.53

headed

0.51

-led

0.47

 Lead

0.47

Activations Density 0.505%

references to governance and organized groups

No Comments

No Known Activations