INDEX

Explanations

terms related to camera lenses and their properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

eur

-0.17

exus

-0.16

lund

-0.16

olver

-0.15

uchen

-0.15

rai

-0.15

heading

-0.15

pper

-0.15

ndef

-0.15

orer

-0.15

POSITIVE LOGITS

yclopedia

0.16

otel

0.16

itter

0.15

0.14

æķħ

0.14

rose

0.14

ÙĪØ¹

0.14

vÃ©

0.14

Activations Density 0.003%

terms related to camera lenses and their properties

No Comments

No Known Activations