INDEX

Explanations

terms related to pre-ordering products or items

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

WithError

-0.15

Ã¤l

-0.15

ven

-0.15

extView

-0.14

èªŀ

-0.14

à¸ĵ

-0.14

ForResult

-0.13

æŁ±

-0.13

 Alle

-0.13

-readable

-0.13

POSITIVE LOGITS

istrovstvÃŃ

0.21

uner

0.16

isman

0.15

nant

0.14

ï½¢

0.14

_named

0.14

anan

0.14

sing

0.13

apl

0.13

*[

0.13

Activations Density 0.006%

terms related to pre-ordering products or items

No Comments

No Known Activations