INDEX

Explanations

terms related to lighting and its attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

acons

-0.15

Fat

-0.15

Meh

-0.14

 when

-0.14

Vu

-0.14

okedex

-0.14

loh

-0.14

SharedPointer

-0.14

 Federation

-0.14

Fat

-0.14

POSITIVE LOGITS

ï¸

0.16

ÃŃky

0.16

Wunused

0.16

ayne

0.15

Ð¼Ð¸Ð½Ð¸

0.15

 Ø§ÙĦØ¨ØŃØ«

0.15

angling

0.15

ROUP

0.14

Activations Density 0.026%

terms related to lighting and its attributes

No Comments

No Known Activations