INDEX

Explanations

numerical data, particularly in the context of scientific or technical information

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

ussen

-0.16

irim

-0.15

endas

-0.15

olicy

-0.15

acker

-0.15

erox

-0.14

iscrim

-0.14

eto

-0.14

ery

-0.14

POSITIVE LOGITS

ruk

0.15

 bubble

0.14

è´

0.14

Few

0.14

it

0.13

-seat

0.13

 Bubble

0.13

adem

0.13

defer

0.13

vg

0.13

Activations Density 0.046%

numerical data, particularly in the context of scientific or technical information

No Comments

No Known Activations