INDEX

Explanations

references to specific years

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

utenant

-0.16

kowski

-0.15

pering

-0.15

arp

-0.14

oteca

-0.13

iero

-0.13

imson

-0.13

Ŀå§ĭ

-0.13

coon

-0.13

meni

-0.13

POSITIVE LOGITS

³

0.14

esso

0.14

_COLL

0.14

flix

0.13

éĹ´

0.13

elah

0.13

ä¸»ä¹ī

0.13

 æ¹

0.13

.dispatcher

0.13

shire

0.13

Activations Density 0.078%

references to specific years

No Comments

No Known Activations