INDEX

Explanations

instances of negation or denial in the text

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

unal

-0.15

 misunderstanding

-0.15

eno

-0.14

iven

-0.14

 TestData

-0.14

ambi

-0.14

ertino

-0.14

ernel

-0.14

amb

-0.13

 Marino

-0.13

POSITIVE LOGITS

 realize

0.41

 realization

0.39

 realise

0.37

 realizes

0.36

 realized

0.36

 realizing

0.33

 realised

0.33

 rÃ©alis

0.28

æĦıè¯Ĩ

0.25

 realiz

0.25

Activations Density 0.077%

instances of negation or denial in the text

No Comments

No Known Activations