INDEX

Explanations

references to boats and related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

uously

-0.19

-0.17

hone

-0.17

gew

-0.16

urons

-0.16

obe

-0.16

 boiler

-0.15

ationally

-0.14

ANTS

-0.14

.dataTables

-0.14

POSITIVE LOGITS

iful

0.23

aroo

0.23

load

0.21

anical

0.20

ies

0.19

camp

0.19

anza

0.18

friend

0.18

ie

0.18

shed

0.18

Activations Density 0.037%

references to boats and related terminology

No Comments

No Known Activations