INDEX

Explanations

inquiries related to personal experiences and reflections on professional choices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

iana

-0.18

Bean

-0.15

ynet

-0.14

mtree

-0.14

pell

-0.14

ButtonItem

-0.14

stown

-0.14

veau

-0.14

uppe

-0.14

 Twice

-0.14

POSITIVE LOGITS

 Pearce

0.15

 ÙĤØ¨ÙĦ

0.14

 Ãĸn

0.13

 RegexOptions

0.13

ennie

0.13

LD

0.13

.Emit

0.12

à¸¡

0.12

 actionTypes

0.12

à¸¡à¸Ļ

0.12

Activations Density 0.152%

inquiries related to personal experiences and reflections on professional choices

No Comments

No Known Activations