INDEX

Explanations

interpersonal interactions 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 @ 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

 Stern

-0.17

anges

-0.15

 å¤ı

-0.14

ophy

-0.14

uke

-0.13

 Forum

-0.13

iw

-0.13

á»£

-0.13

 Stones

-0.13

 Kramer

-0.13

POSITIVE LOGITS

elli

0.16

nik

0.16

'icon

0.15

bole

0.14

ruz

0.14

nici

0.14

à¸ªà¸²à¸¢

0.14

ladu

0.14

unik

0.14

adin

0.13

Activations Density 0.467%

interpersonal interactions and relationships

No Comments

No Known Activations