INDEX

Explanations

mentions of locusts 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 @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

å¹ķ

-0.20

ë§ī

-0.18

itter

-0.16

alat

-0.15

bons

-0.15

istas

-0.14

SOS

-0.14

ior

-0.14

wig

-0.14

\Active

-0.13

POSITIVE LOGITS

inox

0.17

ational

0.16

gan

0.16

tridge

0.16

tega

0.15

estic

0.15

 ÙħØ®Øª

0.15

ATIONS

0.15

ivery

0.15

uhl

0.14

Activations Density 0.014%

mentions of locusts and related terminology

No Comments

No Known Activations