INDEX

Explanations

references to authority figures and groups of people involved in decision-making processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ILA

-0.16

UIT

-0.15

à¹ģà¸Ł

-0.15

/***************************************************************************↵

-0.15

ByVersion

-0.15

ctal

-0.14

ãĥ³ãĤº

-0.14

æŁ±

-0.13

 Breed

-0.13

-wow

-0.13

POSITIVE LOGITS

 upstream

0.15

 authorities

0.15

oger

0.14

 Thomson

0.14

eterminate

0.14

 downstream

0.14

cona

0.14

 Duncan

0.14

merc

0.14

cond

0.13

Activations Density 0.104%

references to authority figures and groups of people involved in decision-making processes

No Comments

No Known Activations