INDEX

Explanations

references to locations and events related to specific establishments or occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

que

-0.16

ylene

-0.15

gu

-0.15

 prop

-0.15

ä¸ĬãģĮ

-0.14

irez

-0.14

avan

-0.14

omor

-0.14

-0.13

POSITIVE LOGITS

ìľ¡

0.17

doch

0.16

ÄĽj

0.16

-ves

0.15

dac

0.15

upertino

0.15

Äįel

0.14

 ÙĨÛĮÙħ

0.14

Å¡em

0.14

ATUS

0.14

Activations Density 0.003%

references to locations and events related to specific establishments or occurrences

No Comments

No Known Activations