INDEX

Explanations

variations of the word "kin" and its derivatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ipmap

-0.15

iro

-0.15

Ø§ÙĦØ¹

-0.15

zych

-0.14

ibri

-0.14

ÑĨÐ¸Ð½

-0.14

rescia

-0.14

çłĤ

-0.14

inline

-0.14

ternet

-0.14

POSITIVE LOGITS

ohan

0.16

 Shall

0.16

Nah

0.14

adastro

0.14

 Ð¿Ð»Ð°

0.14

Ã§a

0.14

 Scalars

0.14

born

0.13

 predecess

0.13

ÑĢÐµÐ¶

0.13

Activations Density 0.005%

variations of the word "kin" and its derivatives

No Comments

No Known Activations