INDEX

Explanations

references to awards or recognition in a competitive context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

Tou

-0.16

 Dahl

-0.15

ilon

-0.15

Ð½ÑĸÑĩ

-0.15

enso

-0.15

ETO

-0.15

ahl

-0.15

-0.14

mlin

-0.14

OAD

-0.14

POSITIVE LOGITS

æĺĩ

0.18

imos

0.17

aÄŁÄ±

0.15

bao

0.15

ba

0.15

 Bailey

0.15

avr

0.15

iglia

0.15

ba

0.14

ç´

0.14

Activations Density 0.030%

references to awards or recognition in a competitive context

No Comments

No Known Activations

references to awards or recognition in a competitive context

No Comments

No Known Activations