INDEX

Explanations

technical terms and references related to computer coding and command definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 intens

-0.16

 createSelector

-0.16

 Miranda

-0.15

az

-0.15

 resp

-0.15

_transient

-0.14

 Cheap

-0.14

 conv

-0.14

åĤĻ

-0.14

POSITIVE LOGITS

EFI

0.27

EFI

0.26

.ef

0.24

Protocol

0.21

_PROTOCOL

0.21

 Protocol

0.20

_protocol

0.19

protocols

0.19

Boot

0.17

_ef

0.17

Activations Density 0.002%

technical terms and references related to computer coding and command definitions

No Comments

No Known Activations