INDEX

Explanations

phrases related to academic and professional credentials or qualifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ependency

-0.17

ooke

-0.15

ãĥ¼ãĥª

-0.15

facility

-0.14

ANTA

-0.14

insky

-0.14

erve

-0.14

HLT

-0.14

aul

-0.13

ruc

-0.13

POSITIVE LOGITS

 management

0.23

 promotion

0.21

 handling

0.21

 manufacture

0.19

 detection

0.18

 study

0.18

 design

0.17

 evaluation

0.17

 conduct

0.17

Activations Density 0.189%

phrases related to academic and professional credentials or qualifications

No Comments

No Known Activations