INDEX

Explanations

instances of the word "showcase" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

Ð½Ð¾ÑģÑĤ

-0.18

ched

-0.17

jac

-0.16

tha

-0.15

eman

-0.15

beiter

-0.15

emble

-0.14

olet

-0.14

á»Ł

-0.14

thic

-0.14

POSITIVE LOGITS

 Bene

0.15

0.14

ively

0.14

egov

0.14

anlÄ±

0.14

Selective

0.14

edx

0.14

eg

0.14

Ø§Ø¨Ø§ÙĨ

0.14

forth

0.13

Activations Density 0.010%

instances of the word "showcase" and its variations

No Comments

No Known Activations