INDEX

Explanations

references to a specific classification or categorization system denoted by alphanumeric codes

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

ime

-0.29

ype

-0.24

rc

-0.20

opc

-0.20

oken

-0.20

ag

-0.19

halt

-0.19

itle

-0.19

imer

-0.19

AG

-0.18

POSITIVE LOGITS

olerance

0.23

issue

0.23

aran

0.23

ad

0.23

etr

0.21

atum

0.21

aurus

0.20

etre

0.20

itled

0.19

onne

0.19

Activations Density 0.077%

references to a specific classification or categorization system denoted by alphanumeric codes

No Comments

No Known Activations