INDEX

Explanations

references to customized or personalized products

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

erson

-0.19

rowse

-0.14

gni

-0.14

ãĤīãģı

-0.14

agedList

-0.14

egov

-0.14

ephy

-0.14

alog

-0.14

áº»

-0.14

 Ð°Ð»

-0.13

POSITIVE LOGITS

.communic

0.15

wed

0.15

order

0.14

exampleInputEmail

0.14

.LENGTH

0.14

æĽ

0.14

à¥Ĥà¤¦

0.14

SION

0.14

æ²Ł

0.14

 ÙħØªØ¹Ø¯Ø¯

0.14

Activations Density 0.070%

references to customized or personalized products

No Comments

No Known Activations