INDEX

Explanations

references to measurements and astronomical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

vice

-0.15

ç«ĭ

-0.15

TextWriter

-0.15

VICE

-0.14

ISCO

-0.14

Managed

-0.14

=>'

-0.14

iyel

-0.14

softmax

-0.13

åį·

-0.13

POSITIVE LOGITS

Hip

0.23

HIP

0.21

HIP

0.21

Hip

0.21

ast

0.19

 stars

0.17

 motions

0.17

 Banc

0.17

mas

0.17

 catalog

0.16

Activations Density 0.010%

references to measurements and astronomical terms

No Comments

No Known Activations