INDEX

Explanations

legal permissions and licenses associated with software

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

elli

-0.17

kinson

-0.16

bat

-0.16

 incremental

-0.15

Miy

-0.15

ows

-0.15

iesen

-0.15

 Justice

-0.15

-0.14

insk

-0.14

POSITIVE LOGITS

upe

0.16

geber

0.16

PARATOR

0.16

ÐµÐºÐ¾Ð¼

0.16

GuidId

0.15

 gratuites

0.15

\xa

0.15

ooled

0.15

onium

0.15

 kabil

0.14

Activations Density 0.028%

legal permissions and licenses associated with software

No Comments

No Known Activations