INDEX

Explanations

instances of the word "presented" to identify the act of presenting information or awards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

İ

-0.17

erox

-0.16

song

-0.15

arend

-0.15

 Harrison

-0.15

aktu

-0.15

hardt

-0.15

li

-0.15

py

-0.15

 reversible

-0.14

POSITIVE LOGITS

erea

0.17

Î½Î¹Î±

0.15

avra

0.15

åľ¨çº¿è§Ĥçľĭ

0.15

abbo

0.15

ucci

0.15

egend

0.14

äº¡

0.14

CLUDING

0.14

ancode

0.14

Activations Density 0.008%

instances of the word "presented" to identify the act of presenting information or awards

No Comments

No Known Activations