INDEX

Explanations

references to emotional experiences and their complexities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ulg

-0.14

azu

-0.14

onymous

-0.14

ÑģÑĥ

-0.14

mej

-0.14

verbatim

-0.14

affen

-0.13

ilde

-0.13

ushman

-0.13

rou

-0.13

POSITIVE LOGITS

ardy

0.17

haft

0.16

 Bracket

0.15

omy

0.15

 ç½

0.14

lotte

0.14

 precis

0.13

ãģĦãģ§

0.13

æĭ¬

0.13

lain

0.13

Activations Density 0.448%

references to emotional experiences and their complexities

No Comments

No Known Activations