INDEX

Explanations

terms related to title or naming conventions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

uchs

-0.17

illery

-0.15

andal

-0.15

ARB

-0.15

á»Ļng

-0.15

essian

-0.14

MOTE

-0.14

 ä½į

-0.14

 miscellaneous

-0.14

-0.13

POSITIVE LOGITS

ultip

0.16

 bait

0.14

resolved

0.14

redirect

0.14

pert

0.14

EntryPoint

0.14

 acad

0.14

ÑĥÐ»Ñİ

0.13

ftware

0.13

.struts

0.13

Activations Density 0.009%

terms related to title or naming conventions in various contexts

No Comments

No Known Activations