INDEX

Explanations

content related to ratings and viewership statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

unning

-0.16

ete

-0.15

 Demir

-0.14

iedo

-0.13

asil

-0.13

Ã¡z

-0.13

chner

-0.13

Kab

-0.13

POSITIVE LOGITS

chedulers

0.17

Feat

0.16

ROTO

0.16

 quot

0.15

cee

0.15

feat

0.15

-LAST

0.15

 semiclass

0.15

thers

0.15

tdown

0.15

Activations Density 0.113%

content related to ratings and viewership statistics

No Comments

No Known Activations