INDEX

Explanations

numerical data, particularly large numbers and counts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

olec

-0.17

REFERRED

-0.16

erno

-0.15

intl

-0.15

.undefined

-0.14

rice

-0.14

aval

-0.14

inding

-0.14

egasus

-0.14

bic

-0.14

POSITIVE LOGITS

³

0.16

ship

0.15

flare

0.14

 ADVISED

0.14

uous

0.14

CTYPE

0.14

pc

0.13

weep

0.13

ment

0.13

Ã³ng

0.13

Activations Density 0.079%

numerical data, particularly large numbers and counts

No Comments

No Known Activations