INDEX

Explanations

references to historical figures and their political significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

lsen

-0.15

iple

-0.15

Î¹Î²

-0.14

inaire

-0.14

 åĳ

-0.14

æĦŁæĥħ

-0.14

apo

-0.14

ÙĥØ§Ø±

-0.14

paged

-0.13

ê³¨

-0.13

POSITIVE LOGITS

 office

0.19

 term

0.18

office

0.17

á»©ng

0.15

avit

0.14

 runApp

0.14

 Office

0.14

nsic

0.14

ëıħ

0.14

 à¤ªà¤¦

0.14

Activations Density 0.060%

references to historical figures and their political significance

No Comments

No Known Activations