INDEX

Explanations

references to a specific individual, Jacqueline Kennedy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

eo

-0.18

 TForm

-0.16

lle

-0.15

ease

-0.15

gebung

-0.14

raci

-0.14

eah

-0.14

 Cunningham

-0.14

ISE

-0.14

asher

-0.14

POSITIVE LOGITS

obi

0.34

obs

0.34

uzzi

0.34

lyn

0.33

opo

0.32

qui

0.31

ques

0.30

into

0.30

inta

0.30

obe

0.27

Activations Density 0.014%

references to a specific individual, Jacqueline Kennedy

No Comments

No Known Activations