INDEX

Explanations

prepositions and conjunctions that indicate relationships or connections between ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

oste

-0.17

.Generation

-0.16

)test

-0.15

/loose

-0.15

 oppon

-0.15

à¥įà¤¦à¤°

-0.15

OMP

-0.15

inski

-0.14

TestingModule

-0.14

vers

-0.14

POSITIVE LOGITS

 Buchanan

0.15

Ang

0.15

progressbar

0.15

/groups

0.14

Ale

0.14

Bor

0.14

chu

0.14

akeup

0.14

alker

0.14

Activations Density 0.000%

prepositions and conjunctions that indicate relationships or connections between ideas

No Comments

No Known Activations