INDEX

Explanations

terms and phrases related to documentation and references in scientific or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 Watkins

-0.15

ongan

-0.15

roc

-0.14

PointF

-0.14

.ibm

-0.14

kos

-0.14

amd

-0.13

 gravity

-0.13

POSITIVE LOGITS

enti

0.15

ÑĥÑĩ

0.14

nda

0.14

 Initial

0.14

aryl

0.13

äº«

0.13

Ä¢

0.13

 Peach

0.13

 Dise

0.13

urch

0.13

Activations Density 0.012%

terms and phrases related to documentation and references in scientific or technical contexts

No Comments

No Known Activations