INDEX

Explanations

quantitative performance metrics of vehicles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

empor

-0.16

ssf

-0.16

ums

-0.15

 Projection

-0.15

ded

-0.15

 trá»«

-0.14

 carriers

-0.14

Ð¾ÑıÐ½

-0.14

 addCriterion

-0.14

(MSG

-0.13

POSITIVE LOGITS

-desktop

0.16

 peninsula

0.16

spb

0.16

roc

0.15

ongyang

0.15

ippi

0.15

 Concrete

0.15

 cáº£i

0.14

areth

0.14

ilan

0.14

Activations Density 0.007%

quantitative performance metrics of vehicles

No Comments

No Known Activations