INDEX

Explanations

references to parking areas and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

Ð³Ð»

-0.16

 Blanch

-0.15

ollipop

-0.15

ramework

-0.15

 "(\<

-0.14

kart

-0.14

à¸¥à¸ĩ

-0.14

 Schedule

-0.14

activex

-0.14

POSITIVE LOGITS

inson

0.19

 parking

0.19

platz

0.17

/feed

0.16

lot

0.15

lek

0.15

dd

0.14

 Parking

0.14

lot

0.14

_lot

0.14

Activations Density 0.010%

references to parking areas and related terms

No Comments

No Known Activations