INDEX

Explanations

terms related to legal matters, particularly those concerning evidence and litigation

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

 responsiveness

-0.15

avery

-0.15

jeme

-0.14

oman

-0.14

sko

-0.14

jem

-0.13

Count

-0.13

 neutrality

-0.13

 confidentiality

-0.13

 Period

-0.13

POSITIVE LOGITS

 extent

0.58

 amount

0.56

 degree

0.55

 level

0.46

extent

0.44

 magnitude

0.43

amount

0.43

degree

0.42

 size

0.37

 nature

0.35

Activations Density 0.465%

terms related to legal matters, particularly those concerning evidence and litigation

No Comments

No Known Activations