INDEX

Explanations

expressions of gratitude and appreciation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Kushner

-0.16

iff

-0.16

.bz

-0.15

 Pleasant

-0.15

ÏĥÎ·

-0.15

ÃŃn

-0.15

ProgressHUD

-0.14

 scope

-0.14

lemen

-0.13

ersh

-0.13

POSITIVE LOGITS

 interest

0.21

apult

0.18

 visita

0.18

 visit

0.17

 choose

0.16

corp

0.16

UPPORT

0.16

 visiting

0.16

 interes

0.16

Activations Density 0.030%

expressions of gratitude and appreciation

No Comments

No Known Activations