INDEX

Explanations

phrases indicating uncertainty or conditions related to actions and outcomes

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

á»Ľ

-0.15

iqu

-0.13

olk

-0.13

 nors

-0.13

istr

-0.13

we

-0.13

czas

-0.13

ar

-0.13

anca

-0.13

ateurs

-0.13

POSITIVE LOGITS

 having

0.35

having

0.26

 Having

0.24

Having

0.24

 knowing

0.20

 being

0.18

 allowing

0.18

 ayant

0.18

 Presence

0.17

 doing

0.17

Activations Density 0.530%

phrases indicating uncertainty or conditions related to actions and outcomes

No Comments

No Known Activations