INDEX

Explanations

specific mentions of companies or institutions

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

sch

-0.17

Ch

-0.17

ichick

-0.17

ch

-0.16

 Burke

-0.16

chas

-0.16

chine

-0.16

Ch

-0.16

ch

-0.16

chen

-0.16

POSITIVE LOGITS

æ®µ

0.17

oppel

0.16

-s

0.15

Ã¨s

0.15

å¹¹

0.15

ast

0.15

Ã¼st

0.14

Ð¸ÐºÐ¸

0.14

ives

0.14

 Gang

0.14

Activations Density 0.044%

specific mentions of companies or institutions

No Comments

No Known Activations