INDEX

Explanations

mentions of meetings, visits, and travel-related actions

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

isia

-0.17

izia

-0.15

ecs

-0.15

isce

-0.15

ooter

-0.14

//---------------------------------------------------------------------------↵↵

-0.14

pite

-0.14

å½

-0.14

/lic

-0.14

pas

-0.14

POSITIVE LOGITS

 visit

0.22

 visits

0.19

.visit

0.18

 personally

0.18

visit

0.16

 visited

0.15

 visiting

0.15

 Visit

0.15

alten

0.14

visited

0.14

Activations Density 0.241%

mentions of meetings, visits, and travel-related actions

No Comments

No Known Activations