INDEX

Explanations

content related to government, policy, and their implications on services or regulations

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

parsers

-0.15

 Adolescent

-0.15

 newcomer

-0.14

 Manufacturers

-0.14

eft

-0.14

structors

-0.14

agens

-0.14

itos

-0.13

ainers

-0.13

aviors

-0.13

POSITIVE LOGITS

 people

0.62

äººä»¬

0.54

 customers

0.47

 consumers

0.46

 citizens

0.43

people

0.42

 patients

0.42

 users

0.41

ppl

0.40

 folks

0.40

Activations Density 2.124%

content related to government, policy, and their implications on services or regulations

No Comments

No Known Activations