INDEX

Explanations

phrases related to human emotions and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

evi

-0.18

idar

-0.16

udad

-0.15

GRES

-0.15

bral

-0.15

æļ®

-0.15

arium

-0.14

ÏĦÎµÎ¹

-0.14

azar

-0.14

enci

-0.14

POSITIVE LOGITS

 Gins

0.15

 beden

0.14

ILD

0.14

 Petro

0.14

Fle

0.14

ÑŁ

0.14

 bulk

0.13

 figure

0.13

 Keywords

0.13

Activations Density 0.110%

phrases related to human emotions and relationships

No Comments

No Known Activations