INDEX

Explanations

references to job roles and responsibilities within an organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

nda

-0.19

oje

-0.15

DATED

-0.15

mine

-0.15

 OTHERWISE

-0.15

 Drake

-0.14

Ã©rÃ©

-0.14

shi

-0.14

 paras

-0.14

elda

-0.14

POSITIVE LOGITS

 responsibility

0.17

Dut

0.17

 responsibilities

0.16

respons

0.16

 responsible

0.15

imat

0.15

ISIBLE

0.15

AFE

0.14

 duties

0.14

Activations Density 0.061%

references to job roles and responsibilities within an organization

No Comments

No Known Activations