INDEX

Explanations

labels and terminology related to astrophysics and theoretical physics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

Ã³st

-0.17

ingers

-0.15

neh

-0.15

adle

-0.15

zin

-0.15

zion

-0.15

et

-0.14

ãĥ¥ãĥ¼

-0.14

Wet

-0.14

avers

-0.14

POSITIVE LOGITS

(NS

0.19

NS

0.19

ns

0.18

/ns

0.18

.ns

0.18

mailer

0.16

(ns

0.16

quared

0.15

ubl

0.15

astos

0.15

Activations Density 0.017%

labels and terminology related to astrophysics and theoretical physics

No Comments

No Known Activations