INDEX

Explanations

characteristics related to quality and effectiveness in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

inem

-0.14

izen

-0.14

 Mutual

-0.14

ror

-0.14

eks

-0.14

 Tamb

-0.14

lessness

-0.13

etic

-0.13

eson

-0.13

ëłĪìĿ´

-0.13

POSITIVE LOGITS

 enough

0.22

 Geile

0.18

ness

0.17

mente

0.16

 Enough

0.15

 Ø¬Ø¯Ø§

0.15

 ones

0.15

NESS

0.15

-looking

0.14

ities

0.14

Activations Density 0.724%

characteristics related to quality and effectiveness in various contexts

No Comments

No Known Activations