INDEX

Explanations

references to collaboration and teamwork in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

Gim

-0.16

ihu

-0.15

Gow

-0.15

gim

-0.15

jal

-0.15

uye

-0.15

ologÃŃa

-0.14

angs

-0.14

POSITIVE LOGITS

Ã´n

0.20

(nome

0.17

produto

0.17

chan

0.17

idade

0.16

.nome

0.16

 mesmo

0.16

 itens

0.15

iÃ£o

0.15

linha

0.15

Activations Density 0.020%

references to collaboration and teamwork in various contexts

No Comments

No Known Activations