INDEX

Explanations

references to academic achievements and positions

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

 presence

-0.15

 overl

-0.15

 gland

-0.13

arna

-0.13

yme

-0.13

 subdiv

-0.13

 overlap

-0.13

Ð³Ñĥ

-0.13

vard

-0.13

éĩįå¤§

-0.13

POSITIVE LOGITS

 Lect

0.31

 visiting

0.28

 Post

0.26

 Assistant

0.26

 Senior

0.26

Post

0.25

 Associate

0.25

Vis

0.25

 associate

0.24

 Reader

0.23

Activations Density 0.096%

references to academic achievements and positions

No Comments

No Known Activations