INDEX

Explanations

phrases related to statistical methods and analyses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

Bid

-0.16

 predicts

-0.15

 predicting

-0.15

agens

-0.15

engin

-0.15

 Merchant

-0.15

POCH

-0.15

ãĥ³ãĥĨãĤ£

-0.14

bid

-0.14

.ReadOnly

-0.14

POSITIVE LOGITS

 censor

0.20

 Rubin

0.19

 Penal

0.19

lrt

0.17

 penal

0.17

 nuisance

0.17

.Dial

0.17

Ðĩ

0.17

gee

0.16

 miss

0.16

Activations Density 0.031%

phrases related to statistical methods and analyses

No Comments

No Known Activations