INDEX

Explanations

references to quantities or numerical values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

teenth

-0.19

elize

-0.17

å¹ħ

-0.17

avanaugh

-0.16

isphere

-0.15

teen

-0.15

egrator

-0.15

ullet

-0.15

ãĥ³ãĥĳ

-0.14

yt

-0.14

POSITIVE LOGITS

PCI

0.16

uckle

0.15

uum

0.15

arding

0.15

ress

0.14

PLE

0.14

å¬

0.14

Hierarchy

0.14

avers

0.14

breadcrumb

0.14

Activations Density 0.046%

references to quantities or numerical values

No Comments

No Known Activations