INDEX

Explanations

instances of questioning or inquiries related to legal proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

uluk

-0.16

ï¼ł

-0.16

inherits

-0.15

.Raise

-0.15

alist

-0.14

resco

-0.14

erca

-0.14

OLEAN

-0.14

 Unsafe

-0.14

TED

-0.14

POSITIVE LOGITS

 Comey

0.27

 McCabe

0.25

 Flynn

0.25

 Steele

0.23

FBI

0.23

 Russia

0.22

 Nunes

0.21

 Mueller

0.20

Fly

0.20

 Rosenstein

0.19

Activations Density 0.053%

instances of questioning or inquiries related to legal proceedings

No Comments

No Known Activations