INDEX

Explanations

mentions of performance evaluation and metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

unami

-0.17

enda

-0.16

icom

-0.15

ÑŁ

-0.15

ij

-0.15

ong

-0.15

ation

-0.15

ãĥ«ãĤ¯

-0.15

utes

-0.15

-0.14

POSITIVE LOGITS

 performance

0.20

 Performance

0.19

-performance

0.19

 improvement

0.17

/per

0.17

FORMANCE

0.16

-minded

0.16

Urb

0.16

performance

0.16

/product

0.16

Activations Density 0.019%

mentions of performance evaluation and metrics

No Comments

No Known Activations