INDEX

Explanations

terminology related to legal and professional decision-making processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

shed

-0.18

bourg

-0.15

egral

-0.15

ä¼ģ

-0.14

EEK

-0.14

 shed

-0.14

 Shed

-0.14

resentation

-0.14

otland

-0.13

neau

-0.13

POSITIVE LOGITS

 discretion

0.44

 subjective

0.44

 personal

0.35

 judgment

0.35

 judgement

0.33

 opinion

0.29

personal

0.28

 individual

0.27

 judgments

0.25

 Personal

0.25

Activations Density 0.172%

terminology related to legal and professional decision-making processes

No Comments

No Known Activations