INDEX

Explanations

items or products characterized by their accompanying features or specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

arat

-0.17

ufe

-0.16

ordinate

-0.15

ender

-0.15

æľīä»Ģä¹Ī

-0.15

lick

-0.14

 Factors

-0.14

aba

-0.14

arity

-0.13

ify

-0.13

POSITIVE LOGITS

 attached

0.29

 accompanying

0.27

stood

0.25

attached

0.24

 associated

0.24

 lots

0.22

 embedded

0.22

 kÃ¨m

0.20

 added

0.20

Attached

0.20

Activations Density 0.188%

items or products characterized by their accompanying features or specifications

No Comments

No Known Activations