INDEX

Explanations

names, particularly those associated with "Lind" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ivas

-0.17

ssize

-0.16

iliate

-0.16

epar

-0.16

ãĥ³ãĤº

-0.16

loat

-0.15

ileged

-0.15

Ð°ÑĢÐ°ÑĤ

-0.14

atham

-0.14

eel

-0.14

POSITIVE LOGITS

gren

0.37

quist

0.34

emann

0.32

strom

0.31

ber

0.30

holm

0.29

erman

0.27

qv

0.27

ahl

0.27

enberg

0.27

Activations Density 0.008%

names, particularly those associated with "Lind" and its variations

No Comments

No Known Activations