INDEX

Explanations

phrases indicating quantities or degrees of comparison

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

anio

-0.20

çĶļèĩ³

-0.16

 hatta

-0.15

itzer

-0.15

 either

-0.15

 tháºŃm

-0.14

 simply

-0.14

 actually

-0.14

 EVEN

-0.14

 even

-0.14

POSITIVE LOGITS

 according

0.21

 until

0.21

until

0.19

 ones

0.19

Until

0.19

 Until

0.18

 partially

0.17

 partly

0.17

according

0.16

ened

0.16

Activations Density 0.024%

phrases indicating quantities or degrees of comparison

No Comments

No Known Activations