INDEX

Explanations

instances and references to specific dates and their corresponding events

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

ronym

-0.18

ron

-0.17

abei

-0.16

 Torrent

-0.16

ora

-0.15

unning

-0.15

ah

-0.15

eti

-0.15

aille

-0.15

ely

-0.14

POSITIVE LOGITS

st

0.20

Ã¡nt

0.16

.scalablytyped

0.16

reuse

0.15

arend

0.15

 otherwise

0.14

UILDER

0.14

 ÅĻÃŃj

0.14

HDR

0.14

sut

0.14

Activations Density 0.019%

instances and references to specific dates and their corresponding events

No Comments

No Known Activations