INDEX

Explanations

phrases that indicate connections or relationships between different entities or individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 ê²°íĺ¼

-0.15

portunity

-0.15

 entirety

-0.15

-0.14

jsonp

-0.13

á»ĩu

-0.13

icides

-0.13

jist

-0.13

ivery

-0.13

vida

-0.13

POSITIVE LOGITS

 ties

0.60

 links

0.52

 connections

0.50

 roots

0.41

connections

0.37

links

0.36

 close

0.36

tie

0.35

 Links

0.34

 Connections

0.34

Activations Density 0.159%

phrases that indicate connections or relationships between different entities or individuals

No Comments

No Known Activations