INDEX

Explanations

references to public transportation, specifically buses and related transit terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

eer

-0.21

SPA

-0.17

aires

-0.17

amura

-0.17

Ã¼st

-0.16

ORY

-0.15

ustin

-0.15

eut

-0.15

ately

-0.15

POSITIVE LOGITS

queda

0.27

loads

0.25

(es

0.23

ines

0.23

kers

0.22

iens

0.22

inness

0.22

load

0.21

ier

0.21

INES

0.21

Activations Density 0.015%

references to public transportation, specifically buses and related transit terms

No Comments

No Known Activations