INDEX

Explanations

nouns and their associations, particularly those related to ratings or evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

su

-0.15

cr

-0.14

 Pump

-0.14

 perman

-0.14

amento

-0.14

 Hind

-0.14

NET

-0.13

.MouseAdapter

-0.13

MainFrame

-0.13

nt

-0.13

POSITIVE LOGITS

bett

0.16

gram

0.16

chet

0.15

irut

0.14

åļ

0.14

SF

0.14

 èİ

0.14

stroy

0.14

/DD

0.14

eldo

0.14

Activations Density 0.018%

nouns and their associations, particularly those related to ratings or evaluations

No Comments

No Known Activations