INDEX

Explanations

references to friends and social connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

itz

-0.19

Ìĥ

-0.17

ors

-0.17

adio

-0.17

itizen

-0.16

OPLE

-0.16

otch

-0.16

ft

-0.15

erse

-0.15

baz

-0.15

POSITIVE LOGITS

liness

0.31

lier

0.30

liest

0.28

ships

0.21

 WithEvents

0.20

lies

0.19

/ac

0.18

ë¨¹

0.16

chaft

0.16

chip

0.15

Activations Density 0.037%

references to friends and social connections

No Comments

No Known Activations