INDEX

Explanations

references to testing frameworks and associated units in programming

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

 past

-0.16

omentum

-0.15

 weather

-0.15

èª¬

-0.14

Pag

-0.14

aten

-0.14

ÄĻd

-0.14

ãĥķãĥ¬

-0.14

Raj

-0.14

li

-0.14

POSITIVE LOGITS

.jupiter

0.15

#+

0.15

 ÑĥÑĤ

0.14

æº

0.14

ÄįÃ¡st

0.14

_decor

0.14

.imag

0.14

ltra

0.14

arten

0.14

:index

0.14

Activations Density 0.005%

references to testing frameworks and associated units in programming

No Comments

No Known Activations