INDEX

Explanations

terms related to electric and hybrid vehicles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

etro

-0.15

allas

-0.14

Ð¾ÑĢÐ¼

-0.14

-level

-0.14

kir

-0.14

ynet

-0.14

leur

-0.14

ali

-0.14

yn

-0.14

apsible

-0.13

POSITIVE LOGITS

ally

0.21

 vehicle

0.20

 vehicles

0.20

-drive

0.19

 Vehicles

0.18

 drive

0.18

 Vehicle

0.18

vehicle

0.17

vehicles

0.17

 mobility

0.16

Activations Density 0.010%

terms related to electric and hybrid vehicles

No Comments

No Known Activations