INDEX

Explanations

terms related to trains and locomotion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

glich

-0.17

afari

-0.16

uan

-0.16

akra

-0.16

ippi

-0.15

eld

-0.15

icorn

-0.15

bags

-0.15

elder

-0.14

empo

-0.14

POSITIVE LOGITS

otive

0.31

 engines

0.20

otion

0.18

 engine

0.17

Ã¶l

0.17

lei

0.17

ot

0.16

ITIVE

0.16

 motive

0.16

 Äĳá»Ļng

0.16

Activations Density 0.002%

terms related to trains and locomotion

No Comments

No Known Activations