INDEX

Explanations

references to social issues and conflicts

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

AttributeValue

-0.15

pedia

-0.15

 onDataChange

-0.15

Ð½ÐºÐ°

-0.14

ENTA

-0.13

lein

-0.13

rÃ¡n

-0.13

 Bless

-0.13

 IConfiguration

-0.13

usz

-0.12

POSITIVE LOGITS

 syndrome

0.36

 attitude

0.30

 scenario

0.29

 mentality

0.28

 Syndrome

0.28

 type

0.26

 approach

0.25

 kind

0.25

 principle

0.24

 phenomenon

0.24

Activations Density 0.336%

references to social issues and conflicts

No Comments

No Known Activations