INDEX

Explanations

references to elevators and related infrastructure

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

ØªØ¨

-0.17

Ð¾ÑĢÐ¾Ð´

-0.16

Fu

-0.15

 cáº§m

-0.14

adius

-0.14

ynam

-0.14

undo

-0.14

Ĥ

-0.14

odia

-0.14

emi

-0.13

POSITIVE LOGITS

 elevator

0.42

 Elev

0.35

 elev

0.34

 lifts

0.29

 Lift

0.29

 lift

0.29

lift

0.26

levator

0.25

.lift

0.20

 thang

0.19

Activations Density 0.053%

references to elevators and related infrastructure

No Comments

No Known Activations