INDEX

Explanations

references to location and context within a narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

tÃŃ

-0.15

CLUDE

-0.14

ÃŃna

-0.14

ards

-0.14

uct

-0.14

eler

-0.14

nze

-0.14

ala

-0.14

ired

-0.14

errat

-0.14

POSITIVE LOGITS

 function

0.21

 charge

0.21

 detriment

0.21

 occasion

0.20

 view

0.18

 front

0.17

 occasions

0.17

 principle

0.16

 term

0.16

function

0.16

Activations Density 0.058%

references to location and context within a narrative

No Comments

No Known Activations