INDEX

Explanations

elements related to public consultation and feedback processes

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

ouri

-0.21

kas

-0.15

iol

-0.15

 awards

-0.14

acional

-0.14

 yearly

-0.14

 Award

-0.14

 award

-0.14

 confession

-0.13

mpp

-0.13

POSITIVE LOGITS

 feedback

0.28

 Stake

0.28

 stake

0.28

 Feedback

0.27

 input

0.25

 public

0.25

feedback

0.25

 comment

0.25

-input

0.24

/input

0.24

Activations Density 0.050%

elements related to public consultation and feedback processes

No Comments

No Known Activations