INDEX

Explanations

discussions related to education and career challenges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Instruction

-0.19

 Instruction

-0.18

rud

-0.17

.WinForms

-0.16

 instructional

-0.16

cesso

-0.15

ylon

-0.15

onica

-0.15

 instruction

-0.14

POSITIVE LOGITS

uni

0.39

Uni

0.33

Uni

0.32

uni

0.30

 studying

0.28

 university

0.26

 Fres

0.26

 degree

0.25

 study

0.25

 revision

0.25

Activations Density 0.107%

discussions related to education and career challenges

No Comments

No Known Activations