INDEX

Explanations

the name "Ab" or its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

-0.20

erence

-0.19

ocha

-0.18

lid

-0.18

eries

-0.18

ozy

-0.17

sx

-0.17

lav

-0.17

lide

-0.16

ox

-0.16

POSITIVE LOGITS

iola

0.24

igail

0.22

ub

0.22

iod

0.22

rahim

0.21

du

0.21

bot

0.20

à¥įà¤¦

0.19

ner

0.19

ducted

0.19

Activations Density 0.009%

the name "Ab" or its variations in different contexts

No Comments

No Known Activations