INDEX

Explanations

mathematical and graph theory concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

æ¹¯

-0.14

cura

-0.14

é£¯

-0.14

èĪį

-0.14

Ø¶ÙĪ

-0.14

æĢĢ

-0.14

ManagedObject

-0.13

ãĥ¼ãĥ

-0.13

aler

-0.13

ouden

-0.13

POSITIVE LOGITS

 permutations

0.23

 Stanley

0.22

pos

0.21

 permutation

0.20

 sortable

0.20

 enumeration

0.19

 word

0.19

jeu

0.19

bij

0.19

 prefixes

0.18

Activations Density 0.055%

mathematical and graph theory concepts

No Comments

No Known Activations