INDEX

Explanations

references to specifications and comparisons of products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

æĪ

-0.15

 automobiles

-0.14

EOF

-0.14

NF

-0.14

 destinationViewController

-0.14

 automobile

-0.14

vette

-0.14

Ð»Ð°Ð·

-0.14

æĪĲ

-0.14

 powered

-0.13

POSITIVE LOGITS

cab

0.22

æ²¹

0.20

 operator

0.19

cab

0.18

 Operator

0.17

unload

0.17

conj

0.17

.Operator

0.16

Cab

0.16

Operators

0.16

Activations Density 0.006%

references to specifications and comparisons of products

No Comments

No Known Activations