INDEX

Explanations

references to social media engagement and communication strategies

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

iefs

-0.15

.nih

-0.14

 æ±

-0.13

omor

-0.13

ÑĥÐ¹

-0.13

.cgi

-0.13

ducted

-0.12

ropol

-0.12

utron

-0.12

Ð¾Ð±Ð¸

-0.12

POSITIVE LOGITS

 social

0.83

social

0.68

 Social

0.67

Social

0.63

 SOCIAL

0.58

-social

0.57

_social

0.56

 Facebook

0.56

 sociale

0.54

.social

0.54

Activations Density 0.436%

references to social media engagement and communication strategies

No Comments

No Known Activations