INDEX

Explanations

references to measurements, dimensions, and specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

iquÃ©

-0.17

 à¹Ĩ

-0.17

izo

-0.15

alice

-0.14

atters

-0.14

 Binder

-0.14

à¹Ĩ

-0.14

ette

-0.14

 arranged

-0.13

 senses

-0.13

POSITIVE LOGITS

 GetMessage

0.16

ãĤ´ãĥª

0.15

each

0.15

 each

0.15

ighton

0.15

inea

0.15

uria

0.15

bout

0.14

cola

0.13

reamble

0.13

Activations Density 0.177%

references to measurements, dimensions, and specifications

No Comments

No Known Activations