INDEX

Explanations

references to official reports or statistical data

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

 Ð²Ð¾ÑĤ

-0.18

coop

-0.15

rij

-0.14

vat

-0.14

arden

-0.14

nel

-0.14

crew

-0.14

ARSE

-0.14

 Accord

-0.14

orthy

-0.14

POSITIVE LOGITS

UPI

0.23

dictions

0.15

 prime

0.15

urb

0.14

Bry

0.14

Ã«r

0.14

 /*!↵

0.14

ekil

0.13

 Morrow

0.13

oming

0.13

Activations Density 0.004%

references to official reports or statistical data

No Comments

No Known Activations

references to official reports or statistical data

No Comments

No Known Activations