INDEX

Explanations

references to the month of March

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

oya

-0.20

agara

-0.16

 christmas

-0.16

hr

-0.15

à¥įà¤§

-0.15

 thá»§

-0.14

oy

-0.14

oh

-0.14

ÅĽcie

-0.14

iswa

-0.14

POSITIVE LOGITS

rd

0.35

 Madness

0.27

March

0.27

 March

0.26

../../../

0.24

-quarters

0.24

andise

0.23

esa

0.23

-Apr

0.23

itecture

0.22

Activations Density 0.041%

references to the month of March

No Comments

No Known Activations