INDEX

Explanations

references to calculations or numeric data involving years and historical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

icer

-0.16

aÃ§

-0.15

Ã¡p

-0.15

 Spaces

-0.14

icari

-0.14

acific

-0.14

abit

-0.14

inge

-0.14

psc

-0.13

Ð¿Ð¾Ð²

-0.13

POSITIVE LOGITS

bol

0.33

Ð±Ð¾Ð»

0.30

bal

0.19

ball

0.18

ÏĥÏĨÎ±

0.17

spiel

0.17

 Sala

0.16

bolt

0.16

.showMessage

0.15

Ð²Ð¾Ð»

0.15

Activations Density 0.026%

references to calculations or numeric data involving years and historical context

No Comments

No Known Activations