INDEX

Explanations

specifications and performance metrics of high-performance vehicles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

vyk

-0.15

Ã©ro

-0.15

lector

-0.15

iou

-0.14

ichtig

-0.14

alu

-0.14

à¸Ĩ

-0.14

ocytes

-0.14

ulur

-0.14

illard

-0.13

POSITIVE LOGITS

 Dart

0.15

 compress

0.14

 strength

0.14

AINS

0.13

ains

0.13

-Jun

0.13

kola

0.13

 Stam

0.13

ophil

0.13

 power

0.12

Activations Density 0.008%

specifications and performance metrics of high-performance vehicles

No Comments

No Known Activations