INDEX

Explanations

references to singular entities and unique identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

inium

-0.15

 equally

-0.15

å½¹

-0.14

Mer

-0.14

/lg

-0.14

 Least

-0.14

 least

-0.14

 Millet

-0.14

aine

-0.14

gang

-0.13

POSITIVE LOGITS

/single

0.22

(single

0.20

tons

0.20

ãģĹãĤĩ

0.18

OrNull

0.17

istrovstvÃŃ

0.17

egrity

0.16

oulos

0.15

-single

0.15

adoo

0.15

Activations Density 0.184%

references to singular entities and unique identifiers

No Comments

No Known Activations