INDEX

Explanations

terms related to sedative drugs and their effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ruba

-0.16

idis

-0.15

 Alternate

-0.15

 æ¿

-0.14

 Brushes

-0.14

 selves

-0.14

.scalablytyped

-0.14

 antibiotics

-0.14

inki

-0.14

æ¿Ģ

-0.14

POSITIVE LOGITS

dia

0.27

 soma

0.23

Lor

0.23

sed

0.22

 Diaz

0.22

 tranquil

0.21

Val

0.21

Sed

0.20

Amb

0.20

epam

0.19

Activations Density 0.036%

terms related to sedative drugs and their effects

No Comments

No Known Activations