INDEX

Explanations

technical terms and code elements related to programming languages and frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

lee

-0.15

.Abstractions

-0.15

 Ð½Ð¸Ð·

-0.15

-0.14

inary

-0.14

 Bran

-0.14

imes

-0.14

ento

-0.13

ðŁ

-0.13

ÑĢÐ¾Ñĩ

-0.13

POSITIVE LOGITS

ES

0.33

es

0.23

ES

0.23

ECM

0.23

babel

0.21

 babel

0.21

 arrow

0.20

bab

0.20

/es

0.20

_ES

0.19

Activations Density 0.042%

technical terms and code elements related to programming languages and frameworks

No Comments

No Known Activations