INDEX

Explanations

references to the term "Greens" and its variations in different contexts

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

apia

-0.16

raised

-0.15

ured

-0.15

 SavaÅŁ

-0.15

ENA

-0.15

NX

-0.14

icont

-0.14

nx

-0.14

Ã¤nn

-0.14

|min

-0.14

POSITIVE LOGITS

Gre

0.36

gre

0.36

GRE

0.30

Gre

0.29

gre

0.29

GRE

0.23

gree

0.21

 Gree

0.21

mlin

0.19

inke

0.19

Activations Density 0.011%

references to the term "Greens" and its variations in different contexts

No Comments

No Known Activations