INDEX

Explanations

references to software and technical integration issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Went

-0.16

orus

-0.16

peare

-0.15

 redes

-0.15

TRL

-0.15

ancel

-0.14

ancellable

-0.14

 Accessibility

-0.14

anco

-0.14

eeper

-0.14

POSITIVE LOGITS

 supported

0.42

 Supported

0.39

-supported

0.35

Supported

0.35

supported

0.34

 support

0.32

_supported

0.32

upported

0.31

 unsupported

0.31

æĶ¯æĮģ

0.29

Activations Density 0.192%

references to software and technical integration issues

No Comments

No Known Activations