INDEX

Explanations

references to relationships and connections between people or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

urance

-0.15

ervice

-0.15

ocache

-0.14

ç§ĭ

-0.14

 Oswald

-0.14

ows

-0.14

 grou

-0.14

ulo

-0.14

zik

-0.13

edido

-0.13

POSITIVE LOGITS

 them

0.23

us

0.22

eux

0.17

them

0.17

èĢħ

0.16

 myself

0.15

 ellos

0.15

 Ð½Ð¸Ñħ

0.15

 ihnen

0.14

.mapping

0.14

Activations Density 0.108%

references to relationships and connections between people or groups

No Comments

No Known Activations