INDEX

Explanations

references to news sources and reporting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

issing

-0.16

 Sellers

-0.14

 impressed

-0.14

orie

-0.14

adj

-0.14

mented

-0.14

Gum

-0.14

announce

-0.13

sis

-0.13

POSITIVE LOGITS

 reporting

0.47

 Reporting

0.38

 reported

0.35

 report

0.35

Reporting

0.34

reported

0.33

-report

0.31

 Reported

0.31

 reports

0.29

 REPORT

0.29

Activations Density 0.047%

references to news sources and reporting

No Comments

No Known Activations