INDEX

Explanations

preferences and choices expressed in the context of favoring one option over another

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

angelo

-0.15

urge

-0.15

.NewLine

-0.15

arkan

-0.15

quee

-0.15

venile

-0.14

enha

-0.14

ãĤĤãĤĬ

-0.14

ocy

-0.14

/her

-0.14

POSITIVE LOGITS

entially

0.52

ential

0.40

ably

0.32

ed

0.20

 option

0.19

abb

0.19

 Option

0.18

ance

0.18

enced

0.18

able

0.17

Activations Density 0.039%

preferences and choices expressed in the context of favoring one option over another

No Comments

No Known Activations