INDEX

Explanations

references to events, conferences, or gatherings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 Gaines

-0.17

 congress

-0.15

 Winds

-0.15

Ð²Ð¸

-0.15

obo

-0.15

 Bang

-0.14

 Coron

-0.14

 borderBottom

-0.13

 Gallagher

-0.13

 Grund

-0.13

POSITIVE LOGITS

arih

0.16

.googlecode

0.15

ogle

0.15

/rss

0.14

aval

0.14

oose

0.14

erton

0.14

ÎķÎĻÎ£

0.14

aign

0.14

ìĿį

0.14

Activations Density 0.016%

references to events, conferences, or gatherings

No Comments

No Known Activations