INDEX

Explanations

references to committees and their activities

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

çĦ¶

-0.18

 RuntimeObject

-0.16

leta

-0.15

committed

-0.15

erre

-0.15

rahim

-0.15

 committing

-0.15

uml

-0.14

 McCart

-0.14

symbol

-0.14

POSITIVE LOGITS

 members

0.30

 member

0.25

members

0.25

 chair

0.24

 chairman

0.23

 meetings

0.23

member

0.23

 Chair

0.23

 meeting

0.22

 Chairs

0.22

Activations Density 0.039%

references to committees and their activities

No Comments

No Known Activations