INDEX

Explanations

phrases that express uncertainty or perceptions about situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

anke

-0.19

ullo

-0.17

 undisclosed

-0.16

otron

-0.15

roit

-0.15

ometr

-0.14

iland

-0.14

isman

-0.14

ugi

-0.14

Ø¬Ø¹

-0.14

POSITIVE LOGITS

 obvious

0.25

 straightforward

0.19

odd

0.18

ox

0.18

 strange

0.18

 like

0.16

 radical

0.15

 simple

0.15

ors

0.15

 backward

0.15

Activations Density 0.069%

phrases that express uncertainty or perceptions about situations

No Comments

No Known Activations