INDEX

Explanations

references to the word "Tangier" and its variations

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

urch

-0.14

Sag

-0.14

iones

-0.14

izin

-0.14

zell

-0.14

ropoda

-0.14

 consent

-0.14

ä¹³

-0.13

ffective

-0.13

zung

-0.13

POSITIVE LOGITS

ential

0.31

entially

0.29

 tang

0.24

ents

0.22

ible

0.19

IBLE

0.19

encies

0.18

ibles

0.18

ENTIAL

0.18

entials

0.17

Activations Density 0.007%

references to the word "Tangier" and its variations

No Comments

No Known Activations