INDEX

Explanations

terms indicating size or scale

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

lessly

-0.17

rary

-0.16

resp

-0.15

dit

-0.14

ving

-0.14

±

-0.14

ray

-0.14

ØµÙĩ

-0.14

 resp

-0.14

POSITIVE LOGITS

-scale

0.41

 scale

0.23

-sized

0.21

/small

0.21

Scale

0.20

scale

0.20

 Scale

0.19

gest

0.19

hetto

0.19

/big

0.19

Activations Density 0.146%

terms indicating size or scale

No Comments

No Known Activations