INDEX

Explanations

references to publications and their historical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Depot

-0.15

Ã©l

-0.14

py

-0.14

nob

-0.14

reece

-0.14

 Invent

-0.14

 FUNC

-0.14

 qualifier

-0.13

EventType

-0.13

 Tall

-0.13

POSITIVE LOGITS

interpre

0.18

 interpretations

0.18

Rai

0.18

 Cant

0.18

 interpretation

0.17

 interpre

0.17

interpret

0.17

 cant

0.17

 interpret

0.17

cant

0.16

Activations Density 0.015%

references to publications and their historical context

No Comments

No Known Activations