INDEX

Explanations

references to telecommunications technology and service features

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

-0.15

acha

-0.15

 doma

-0.15

duit

-0.14

egis

-0.14

 Ease

-0.14

 Canter

-0.14

unf

-0.14

inous

-0.14

 unst

-0.14

POSITIVE LOGITS

[]=$

0.17

é¾į

0.16

iteDatabase

0.15

enschaft

0.15

ovÃŃ

0.15

ÐµÐ»ÑĮÐ·Ñı

0.15

issen

0.14

SCALL

0.14

_coverage

0.14

 Franken

0.14

Activations Density 0.019%

references to telecommunications technology and service features

No Comments

No Known Activations