INDEX

Explanations

specific terms and concepts related to a particular organization or classification system

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Ð¸ÑĩÐµÑģÑĤÐ²Ð¾

-0.25

 erste

-0.24

stvo

-0.23

 weitere

-0.23

 Ð´ÑĢÑĥÐ³Ð¸Ðµ

-0.22

ÐµÑĩÐµÐ½Ð¸Ðµ

-0.22

 andere

-0.21

 ÑĸÐ½ÑĪÑĸ

-0.21

 neue

-0.21

 verschiedene

-0.21

POSITIVE LOGITS

Ð½Ð¾Ð³Ð¾

0.40

Ð¾Ð²Ð¾Ð³Ð¾

0.36

ÑģÐºÐ¾Ð³Ð¾

0.35

ÐµÐ½Ð½Ð¾Ð³Ð¾

0.35

ÑĪÐµÐ³Ð¾

0.34

ÐºÐ¾Ð³Ð¾

0.33

Ð°Ð»ÑĮÐ½Ð¾Ð³Ð¾

0.33

Ð¾ÑĩÐ½Ð¾Ð³Ð¾

0.32

ÑģÑĤÐ²ÐµÐ½Ð½Ð¾Ð³Ð¾

0.31

Ð¸ÑĤÐµÐ»ÑĮÐ½Ð¾Ð³Ð¾

0.31

Activations Density 0.053%

specific terms and concepts related to a particular organization or classification system

No Comments

No Known Activations