INDEX

Explanations

references to students and issues related to education and discrimination

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

uw

-0.16

Arb

-0.15

æĭĽèģĺ

-0.15

Î¬Î½Î¹

-0.15

 incompatible

-0.14

 billeder

-0.13

ÑĢÐ°Ð·Ð´

-0.13

chem

-0.13

ks

-0.13

kas

-0.13

POSITIVE LOGITS

 attend

0.85

 attending

0.83

 attends

0.75

 attended

0.73

 attendance

0.72

attend

0.69

 Attend

0.65

 Attendance

0.60

attendance

0.60

attended

0.60

Activations Density 0.253%

references to students and issues related to education and discrimination

No Comments

No Known Activations