INDEX

Explanations

references to specific time periods or decades

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ause

-0.18

æł·çļĦ

-0.14

esar

-0.14

arna

-0.14

ãģ¨ãģĵãĤį

-0.14

 then

-0.13

laus

-0.13

Ð¾Ð´ÐµÐ¹ÑģÑĤÐ²

-0.13

POSITIVE LOGITS

-long

0.24

-old

0.20

esimal

0.16

-plus

0.16

inte

0.15

_dyn

0.15

ToFit

0.15

bul

0.15

aversal

0.15

YNAM

0.15

Activations Density 0.019%

references to specific time periods or decades

No Comments

No Known Activations