INDEX

Explanations

terms related to commemorations and remembrances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ska

-0.18

astos

-0.16

æ²Ł

-0.15

Ð°ÑĢÑħ

-0.15

itudes

-0.14

ugin

-0.14

agem

-0.14

isman

-0.14

apter

-0.14

beg

-0.14

POSITIVE LOGITS

orative

0.48

oration

0.39

mor

0.28

orate

0.26

Ð¾ÑĢÐ°ÑĤÐ¸Ð²

0.21

eration

0.20

ulative

0.19

orial

0.19

urate

0.18

omor

0.18

Activations Density 0.004%

terms related to commemorations and remembrances

No Comments

No Known Activations

terms related to commemorations and remembrances

No Comments

No Known Activations