INDEX

Explanations

references to specific dates or events, particularly those associated with March

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

agara

-0.19

oya

-0.19

hr

-0.17

ÅĽcie

-0.16

onse

-0.15

iswa

-0.14

à¥įà¤§

-0.14

IPC

-0.14

aterno

-0.14

hte

-0.14

POSITIVE LOGITS

March

0.32

 March

0.31

 Madness

0.31

esa

0.28

andise

0.28

rd

0.26

itecture

0.26

-Apr

0.26

 march

0.24

mont

0.23

Activations Density 0.032%

references to specific dates or events, particularly those associated with March

No Comments

No Known Activations