INDEX

Explanations

encoded representations or codes related to various data formats and structures

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

STANCE

-0.15

èıĮ

-0.14

stance

-0.14

ÏĦÎ¿

-0.13

_gp

-0.13

Ð¸ÑĩÐ°

-0.13

inders

-0.13

PERT

-0.13

AMPL

-0.13

pod

-0.13

POSITIVE LOGITS

 prediction

0.24

 coding

0.24

bit

0.22

 scalable

0.22

 video

0.22

 intra

0.21

 transform

0.21

 bitrate

0.21

 motion

0.21

 pyramid

0.21

Activations Density 0.003%

encoded representations or codes related to various data formats and structures

No Comments

No Known Activations