INDEX

Explanations

mentions of organized activities and programs related to debate

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

endencies

-0.16

herence

-0.16

Ã¨n

-0.14

luÅ¾

-0.13

itÃ©s

-0.13

 darn

-0.13

akov

-0.13

lsa

-0.13

urning

-0.13

enen

-0.13

POSITIVE LOGITS

-specific

0.24

 itself

0.23

-related

0.19

 specific

0.17

/cms

0.16

-exclusive

0.16

-friendly

0.15

 samot

0.15

 Nicholson

0.15

related

0.14

Activations Density 0.728%

mentions of organized activities and programs related to debate

No Comments

No Known Activations