INDEX

Explanations

terms related to software libraries and document generation tools

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 Rubin

-0.16

/Foundation

-0.16

 landing

-0.15

mÃ¡

-0.14

rub

-0.14

 Vict

-0.14

èįī

-0.14

thy

-0.14

aseline

-0.14

 hust

-0.13

POSITIVE LOGITS

 Batch

0.20

 batch

0.20

_batch

0.19

 Bulk

0.19

Batch

0.18

_BATCH

0.18

batch

0.18

.batch

0.18

bulk

0.18

æī¹

0.18

Activations Density 0.147%

terms related to software libraries and document generation tools

No Comments

No Known Activations