INDEX

Explanations

phrases related to imprisonment and sentencing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

-0.17

eday

-0.17

apsible

-0.15

ÙĪØ§Ø±

-0.14

Sle

-0.14

uras

-0.14

 Julien

-0.14

pton

-0.14

oris

-0.14

Ø®Ø§ÙĨÙĩ

-0.14

POSITIVE LOGITS

 sentence

0.48

 Sent

0.48

 sentences

0.46

sent

0.45

 SENT

0.45

Sent

0.44

 sent

0.42

.sent

0.40

SENT

0.38

sentence

0.37

Activations Density 0.046%

phrases related to imprisonment and sentencing

No Comments

No Known Activations