INDEX

Explanations

technical jargon and specifications related to automobile design and engineering

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 Sesso

-0.19

ullo

-0.16

acades

-0.15

etten

-0.15

ernes

-0.15

\OptionsResolver

-0.15

ossier

-0.14

rell

-0.14

posables

-0.14

Ø§ÙĦØ¥ÙĨØ¬ÙĦÙĬØ²ÙĬØ©

-0.14

POSITIVE LOGITS

ORED

0.15

IEW

0.14

²

0.14

 tÃ¼r

0.13

GI

0.13

|/

0.13

ndef

0.13

EW

0.13

èĪ

0.13

Activations Density 0.015%

technical jargon and specifications related to automobile design and engineering

No Comments

No Known Activations