INDEX

Explanations

phrases indicating suitability or recommendations for products and services tailored to individual needs

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

imar

-0.17

argin

-0.17

ONS

-0.16

edia

-0.15

ogui

-0.15

Ø´Ùĩ

-0.14

ican

-0.14

inar

-0.14

 tape

-0.14

iner

-0.14

POSITIVE LOGITS

ObjectContext

0.19

 given

0.18

 particular

0.17

 GIVEN

0.17

gnore

0.16

.opensource

0.16

given

0.16

utherford

0.15

fit

0.15

 situation

0.15

Activations Density 0.072%

phrases indicating suitability or recommendations for products and services tailored to individual needs

No Comments

No Known Activations