INDEX

Explanations

instances of character names and their attributes

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

McD

-0.27

ãĥ³ãĥī

-0.24

bd

-0.23

ãĥ«ãĥī

-0.22

bd

-0.21

BD

-0.21

GD

-0.21

ãĥī

-0.21

Bd

-0.20

ourd

-0.20

POSITIVE LOGITS

ide

0.38

ided

0.34

ides

0.32

IDE

0.30

idea

0.29

ideas

0.29

Ide

0.28

side

0.26

ide

0.26

idebar

0.25

Activations Density 0.074%

instances of character names and their attributes

No Comments

No Known Activations